{"version":"e0dfd71514","count":103,"papers":[{"representation":["Template","Point Cloud"],"task":["Human","Scene"],"category":"Video-to-4D","projectPage":"https://fanegg.github.io/Human3R/","paperUrl":"https://arxiv.org/abs/2510.06219","codeUrl":"https://github.com/fanegg/Human3R","tags":[],"motion":["Articulation"],"codeAvailability":true,"interaction":"Human-Scene Interaction","bibtex":"@article{chen2025human3r,     title={Human3R: Everyone Everywhere All at Once},     author={Chen, Yue and Chen, Xingyu and Xue, Yuxuan and Chen, Anpei and Xiu, Yuliang and Gerard, Pons-Moll},     journal={arXiv preprint arXiv:2510.06219},     year={2025}     }","title":"Human3R: Everyone Everywhere All at Once","authors":["Yue Chen","Xingyu Chen","Yuxuan Xue","Anpei Chen","Yuliang Xiu","Pons-Moll Gerard"],"year":"2026","venue":"ICLR","dataset":false,"survey":false,"bibkey":"chen2025human3r","prior":"TD","inputCondition":"Video","trainingStrategy":"Feed-forward","filename":"human3r.json","thumbnailUrl":"images/human3r.webp"},{"title":"ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation","authors":["Hongjie Li","Hong-Xing Yu","Jiaman Li","Jiajun Wu"],"year":"2026","venue":"3DV","paperUrl":"https://arxiv.org/abs/2412.18600","projectPage":"https://awfuact.github.io/zerohsi/","codeUrl":"","representation":["Template","Gaussian Splatting"],"motion":["Articulation"],"prior":"FM","inputCondition":"Text+Scene","trainingStrategy":"Per-scene","interactionType":"HSI","task":"Human","category":[],"tags":[],"interaction":"","codeAvailability":false,"dataset":false,"survey":false,"doi":"","bibtex":"@article{li2024zerohsi,\n  title={ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation},\n  author={Li, Hongjie and Yu, Hong-Xing and Li, Jiaman and Wu, Jiajun},\n  journal={arXiv preprint arXiv:2412.18600},\n  year={2024}\n}","bibkey":"li2024zerohsi","filename":"zerohsi.json","thumbnailUrl":"images/zerohsi.webp"},{"representation":["Gaussian Splatting"],"task":"Scene","category":["Image-to-4D"],"projectPage":"https://4dlrm.github.io/","paperUrl":"https://arxiv.org/pdf/2506.18890","codeUrl":"https://github.com/Mars-tin/4D-LRM","tags":[],"motion":["Space-Time"],"codeAvailability":true,"interaction":"","bibtex":"@misc{ma20254dlrmlargespacetimereconstruction,title={4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time},author={Ziqiao Ma and Xuweiyi Chen and Shoubin Yu and Sai Bi and Kai Zhang and Chen Ziwen and Sihan Xu and Jianing Yang and Zexiang Xu and Kalyan Sunkavalli and Mohit Bansal and Joyce Chai and Hao Tan},year={2025},eprint={2506.18890},archivePrefix={arXiv},primaryClass={http://cs.cv/},url={https://arxiv.org/abs/2506.18890},}","title":"4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time","authors":["Ziqiao Ma","Xuweiyi Chen","Shoubin Yu","Sai Bi","Kai Zhang","Chen Ziwen","Sihan Xu","Jianing Yang","Zexiang Xu","Kalyan Sunkavalli","Mohit Bansal","Joyce Chai","Hao Tan"],"year":"2025","venue":"NeurIPS","dataset":false,"survey":false,"bibkey":"ma20254d","prior":"TD","inputCondition":"Few-Image","trainingStrategy":"Feed-forward","filename":"4dlrm.json","thumbnailUrl":"images/4dlrm.webp"},{"title":"4DNeX: Feed-Forward 4D Generative Modeling Made Easy","authors":["Zhaoxi Chen","Tianqi Liu","Long Zhuo","Jiawei Ren","Zeng Tao","He Zhu","Fangzhou Hong","Liang Pan","Ziwei Liu"],"year":"2025","venue":"ArXiv","paperUrl":"https://arxiv.org/abs/2508.13154","projectPage":"https://4dnex.github.io/","codeUrl":"https://github.com/3DTopia/4DNeX","representation":["Point Cloud"],"motion":["Space-Time"],"prior":"FM+TD","inputCondition":"Image","trainingStrategy":"Feed-forward","interactionType":"","task":"Scene","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@article{4dnex,\n  title={4DNeX: Feed-Forward 4D Generative Modeling Made Easy},\n  author={Zhaoxi Chen and Tianqi Liu and Long Zhuo and Jiawei Ren and Zeng Tao and He Zhu and Fangzhou Hong and Liang Pan and Ziwei Liu},\n  journal={arXiv preprint arXiv:2508.13154},\n  year={2025}\n}","filename":"4dnex.json","thumbnailUrl":"images/4dnex.webp"},{"representation":"","task":"","category":"","projectPage":"","paperUrl":"https://arxiv.org/abs/2503.14501","codeUrl":"https://github.com/MiaoQiaowei/Awesome-4D","tags":[],"motion":"","codeAvailability":true,"interaction":"","bibtex":"@article{miao2025advances, title={Advances in 4d generation: A survey}, author={Miao, Qiaowei and Li, Kehan and Quan, Jinsheng and Min, Zhiyuan and Ma, Shaojie and Xu, Yichao and Yang, Yi and Liu, Ping and Luo, Yawei}, journal={arXiv preprint arXiv:2503.14501}, year={2025} }","dataset":false,"survey":true,"title":"Advances in 4d generation: A survey","authors":["Qiaowei Miao","Kehan Li","Jinsheng Quan","Zhiyuan Min","Shaojie Ma","Yichao Xu","Yi Yang","Ping Liu","Yawei Luo"],"year":"2025","venue":"ArXiv","filename":"ad4d.json","thumbnailUrl":"images/ad4d.webp"},{"representation":"","task":"","category":"","projectPage":"","paperUrl":"https://arxiv.org/abs/2505.10049","codeUrl":"","tags":[],"motion":"","codeAvailability":false,"interaction":"","bibtex":"@article{fan2025advances, title={Advances in Radiance Field for Dynamic Scene: From Neural Field to Gaussian Field}, author={Fan, Jinlong and Zeng, Xuepu and Zhang, Jing and Gong, Mingming and Yang, Yuxiang and Tao, Dacheng}, journal={arXiv preprint arXiv:2505.10049}, year={2025} }","dataset":false,"survey":true,"title":"Advances in Radiance Field for Dynamic Scene: From Neural Field to Gaussian Field","authors":["Jinlong Fan","Xuepu Zeng","Jing Zhang","Mingming Gong","Yuxiang Yang","Dacheng Tao"],"year":"2025","venue":"ArXiv","filename":"dysurvey.json","thumbnailUrl":"images/dysurvey.webp"},{"representation":["Mesh"],"task":"Object","category":["3D-to-4D"],"projectPage":"https://animateanymesh.github.io/AnimateAnyMesh/","paperUrl":"https://arxiv.org/pdf/2506.09982","codeUrl":"https://github.com/JarrentWu1031/AnimateAnyMesh","tags":[],"motion":["Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@article{wu2025animateanymesh,     author = {Wu, Zijie and Yu, Chaohui and Wang, Fan and Bai, Xiang.},     title  = {AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation},     journal = {ICCV},     year   = {2025}, }","title":"AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation","authors":["Zijie Wu","Chaohui Yu","Fan Wang","Xiang. Bai"],"year":"2025","venue":"ICCV","dataset":false,"survey":false,"bibkey":"wu2025animateanymesh","prior":"TD","inputCondition":"Text+Mesh","trainingStrategy":"Feed-forward","filename":"animateanymesh.json","thumbnailUrl":"images/animateanymesh.webp"},{"representation":["Template"],"task":"Object","category":"3D-to-4D","projectPage":"https://anytop2025.github.io/Anytop-page/","paperUrl":"https://arxiv.org/abs/2502.17327","codeUrl":"https://github.com/Anytop2025/Anytop","tags":[],"motion":["Articulation"],"codeAvailability":true,"interaction":"","bibtex":"@article{gat2025anytop,                 title={AnyTop: Character Animation Diffusion with Any Topology},                 author={Gat, Inbar and Raab, Sigal and Tevet, Guy and Reshef, Yuval and Bermano, Amit H and Cohen-Or, Daniel},                 journal={SIGGRAPH},                 year={2025}               }","title":"AnyTop: Character Animation Diffusion with Any Topology","authors":["Inbar Gat","Sigal Raab","Guy Tevet","Yuval Reshef","Amit H Bermano","Daniel Cohen-Or"],"year":"2025","venue":"SIGGRAPH","dataset":false,"survey":false,"bibkey":"gat2025anytop","prior":"TD","inputCondition":"Skeleton","trainingStrategy":"Feed-forward","filename":"anytop.json","thumbnailUrl":"images/anytop.webp"},{"representation":["Part","Mesh"],"task":"Object","category":"3D-to-4D","projectPage":"https://articulate-anymesh.github.io/","paperUrl":"https://arxiv.org/abs/2502.02590","codeUrl":"https://github.com/UMass-Embodied-AGI/Articulate-Anymesh","tags":[],"motion":["Articulation"],"codeAvailability":true,"interaction":"","bibtex":"@article{qiu2025articulate,   title={Articulate anymesh: Open-vocabulary 3d articulated objects modeling},   author={Qiu, Xiaowen and Yang, Jincheng and Wang, Yian and Chen, Zhehuan and Wang, Yufei and Wang, Tsun-Hsuan and Xian, Zhou and Gan, Chuang},   journal={CoRL},   year={2025} }","title":"Articulate anymesh: Open-vocabulary 3d articulated objects modeling","authors":["Xiaowen Qiu","Jincheng Yang","Yian Wang","Zhehuan Chen","Yufei Wang","Tsun-Hsuan Wang","Zhou Xian","Chuang Gan"],"year":"2025","venue":"CoRL","dataset":false,"survey":false,"bibkey":"qiu2025articulate","prior":"FM+LLM","inputCondition":"Mesh","trainingStrategy":"Per-scene","filename":"articulateanymesh.json","thumbnailUrl":"images/articulateanymesh.webp"},{"representation":["Part","Gaussian Splatting"],"task":"Object","category":"Image-to-4D","projectPage":"https://guojunfu-tech.github.io/articulatedGS-io/","paperUrl":"https://arxiv.org/abs/2503.08135","codeUrl":"https://github.com/GuoJunfu-tech/ArticulatedGaussians","tags":[],"motion":["Articulation"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{guo2025articulatedgs, title={Articulatedgs: Self-supervised digital twin modeling of articulated objects using 3d gaussian splatting}, author={Guo, Junfu and Xin, Yu and Liu, Gaoyi and Xu, Kai and Liu, Ligang and Hu, Ruizhen}, booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference}, pages={27144--27153}, year={2025} }","title":"Articulatedgs: Self-supervised digital twin modeling of articulated objects using 3d gaussian splatting","authors":["Junfu Guo","Yu Xin","Gaoyi Liu","Kai Xu","Ligang Liu","Ruizhen Hu"],"year":"2025","venue":"CVPR","dataset":false,"survey":false,"bibkey":"guo2025articulatedgs","prior":"Input","inputCondition":"Image","trainingStrategy":"Per-scene","filename":"articulatedgs.json","thumbnailUrl":"images/articulatedgs.webp"},{"representation":["Template","NeRF"],"task":"Human","category":"Image-to-4D","projectPage":"https://kumapowerliu.github.io/AvatarArtist/","paperUrl":"https://arxiv.org/abs/2503.19906","codeUrl":"https://github.com/ant-research/AvatarArtist","tags":[],"motion":["Articulation","Deformation"],"codeAvailability":true,"interaction":"","bibtex":" @inproceedings{liu2025avatarartist,     author    = {Hongyu Liu, Xuan Wang, Ziyu Wan, Yue Ma, Jingye Chen, Yanbo Fan, Yujun Shen, Yibing Song, Qifeng Chen },     title     = {AvatarArtist: Open-Domain 4D Avatarization},     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},     year      = {2025}}","title":"AvatarArtist: Open-Domain 4D Avatarization","authors":["Xuan Wang, Ziyu Wan, Yue Ma, Jingye Chen, Yanbo Fan, Yujun Shen, Yibing Song, Qifeng Chen Hongyu Liu"],"year":"2025","venue":"CVPR","dataset":false,"survey":false,"bibkey":"liu2025avatarartist","prior":"FM+TD","inputCondition":"Image","trainingStrategy":"Feed-forward","filename":"avatarartist.json","thumbnailUrl":"images/avatarartist.webp"},{"representation":["Template","Gaussian Splatting"],"task":"Human","category":"Text-to-4D","projectPage":"https://yukangcao.github.io/AvatarGO/","paperUrl":"https://arxiv.org/abs/2410.07164","codeUrl":"https://github.com/yukangcao/AvatarGO","tags":[],"motion":["Articulation","Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@article{cao2024avatargo,   title={Avatargo: Zero-shot 4d human-object interaction generation and animation},   author={Cao, Yukang and Pan, Liang and Han, Kai and Wong, Kwan-Yee K and Liu, Ziwei},   journal={ICLR},   year={2025} }","title":"Avatargo: Zero-shot 4d human-object interaction generation and animation","authors":["Yukang Cao","Liang Pan","Kai Han","Kwan-Yee K Wong","Ziwei Liu"],"year":"2025","venue":"ICLR","dataset":false,"survey":false,"bibkey":"cao_avatargo_2024","prior":"FM+LLM","inputCondition":"Text","trainingStrategy":"Per-scene","interactionType":"HOI","filename":"avatargo.json","thumbnailUrl":"images/avatargo.webp"},{"title":"BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting","authors":["Jeongwan On","Kyeonghwan Gwak","Gunyoung Kang","Junuk Cha","Soohyun Hwang","Hyein Hwang","Seungryul Baek"],"year":"2025","venue":"CVPR","paperUrl":"https://arxiv.org/abs/2504.09097","projectPage":"","codeUrl":"https://github.com/On-JungWoan/BIGS","representation":["Template","Gaussian Splatting"],"motion":["Articulation"],"prior":"FM+Input","inputCondition":"Video","trainingStrategy":"Per-scene","interactionType":"Hand-O","task":"Hand","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{on2025bigs,\n  title={BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting},\n  author={On, Jeongwan and Gwak, Kyeonghwan and Kang, Gunyoung and Cha, Junuk and Hwang, Soohyun and Hwang, Hyein and Baek, Seungryul},\n  booktitle={CVPR},\n  year={2025}\n}","bibkey":"on2025bigs","filename":"bigs.json","thumbnailUrl":"images/bigs.webp"},{"representation":["Part","Gaussian Splatting"],"task":["Object","Scene"],"category":"Image-to-4D","projectPage":"https://articulate-gs.github.io/","paperUrl":"https://arxiv.org/abs/2502.19459","codeUrl":"https://github.com/YuLiu-LY/ArtGS","tags":[],"motion":["Articulation"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{liu2025building,   title={Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting},   author={Liu, Yu and Jia, Baoxiong and Lu, Ruijie and Ni, Junfeng and Zhu, Song-Chun and Huang, Siyuan},   booktitle={The Thirteenth International Conference on Learning Representations},   year={2025}, }","title":"Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting","authors":["Yu Liu","Baoxiong Jia","Ruijie Lu","Junfeng Ni","Song-Chun Zhu","Siyuan Huang"],"year":"2025","venue":"ICLR","dataset":true,"survey":false,"bibkey":"liu2025artgs","prior":"Input","inputCondition":"Image","trainingStrategy":"Per-scene","filename":"artgs.json","thumbnailUrl":"images/artgs.webp"},{"representation":["Template","Gaussian Splatting"],"task":"Human","category":"Image-to-4D","projectPage":"https://felixtaubner.github.io/cap4d/","paperUrl":"https://arxiv.org/abs/2412.12093","codeUrl":"https://github.com/felixtaubner/cap4d","tags":[],"motion":["Articulation","Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{taubner2025cap4d, author    = {Taubner, Felix and Zhang, Ruihang and Tuli, Mathieu and Lindell, David B.},     title     = {CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models},     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},     month     = {June},     year      = {2025},     pages     = {5318-5330} }","title":"CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models","authors":["Felix Taubner","Ruihang Zhang","Mathieu Tuli","David B. Lindell"],"year":"2025","venue":"CVPR","dataset":false,"survey":false,"bibkey":"taubner2025cap4d","prior":"FM+TD","inputCondition":"Image","trainingStrategy":"Hybrid","filename":"cap4d.json","thumbnailUrl":"images/cap4d.webp"},{"representation":["Gaussian Splatting"],"task":"Scene","category":["Video-to-4D","Image-to-4D"],"projectPage":"https://cat-4d.github.io/","paperUrl":"https://arxiv.org/pdf/2411.18613","codeUrl":"","tags":[],"motion":["Deformation"],"codeAvailability":false,"interaction":"","bibtex":"@article{wu2024cat4d,title={{CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models}},author={Wu, Rundi and Gao, Ruiqi and Poole, Ben and Trevithick, Alex and Zheng, Changxi and Barron, Jonathan T. and Holynski, Aleksander}journal={CVPR},year={2025}}","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","authors":["Rundi Wu","Ruiqi Gao","Ben Poole","Alex Trevithick","Changxi Zheng","Jonathan T. Barron","Aleksander Holynski"],"year":"2025","venue":"CVPR","dataset":false,"survey":false,"bibkey":"wu2025cat4d","prior":"FM+TD","inputCondition":"Video","trainingStrategy":"Hybrid","filename":"cat4d.json","thumbnailUrl":"images/cat4d.webp"},{"representation":["Point Cloud"],"task":"Scene","category":"Image-to-4D","projectPage":"https://cut3r.github.io/","paperUrl":"http://arxiv.org/abs/2501.12387","codeUrl":"https://github.com/CUT3R/CUT3R","tags":[],"motion":["Per frame"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{cut3r,  Author = {Qianqian Wang* and Yifei Zhang* and Aleksander Holynski and Alexei A. Efros and Angjoo Kanazawa},         Title = {Continuous 3D Perception Model with Persistent State},         Year = {2025},           booktitle={CVPR},         }","title":"Continuous 3D Perception Model with Persistent State","authors":["Qianqian Wang*","Yifei Zhang*","Aleksander Holynski","Alexei A. Efros","Angjoo Kanazawa"],"year":"2025","venue":"CVPR","dataset":false,"survey":false,"bibkey":"cut3r","prior":"TD","inputCondition":"Image","trainingStrategy":"Feed-forward","filename":"cut3r.json","thumbnailUrl":"images/cut3r.webp"},{"title":"CoopDiff: Anticipating 3D Human-object Interactions via Contact-consistent Decoupled Diffusion","authors":["Xiaotong Lin","Tianming Liang","Jian-Fang Hu","Kun-Yu Lin","Yulei Kang","Chunwei Tian","Jianhuang Lai","Wei-Shi Zheng"],"year":"2025","venue":"ArXiv","paperUrl":"https://arxiv.org/abs/2508.07162","projectPage":"","codeUrl":"","representation":["Template","Mesh"],"motion":["Articulation"],"prior":"TD","inputCondition":"Motion","trainingStrategy":"Feed-forward","interactionType":"HOI","task":"Human","category":[],"tags":[],"interaction":"","codeAvailability":false,"dataset":false,"survey":false,"doi":"","bibtex":"@article{coopdiff,\n  title={CoopDiff: Anticipating 3D Human-object Interactions via Contact-consistent Decoupled Diffusion},\n  author={Xiaotong Lin and Tianming Liang and Jian-Fang Hu and Kun-Yu Lin and Yulei Kang and Chunwei Tian and Jianhuang Lai and Wei-Shi Zheng},\n  journal={arXiv preprint arXiv:2508.07162},\n  year={2025}\n}","filename":"coopdiff.json","thumbnailUrl":"images/coopdiff.webp"},{"representation":["Template","Gaussian Splatting"],"task":"Human","category":"Image-to-4D","projectPage":"https://disco-4d.github.io/","paperUrl":"https://arxiv.org/pdf/2409.17280","codeUrl":"https://github.com/disco-4d/Disco4D","tags":[],"motion":["Articulation","Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{   title={Disco4D: Disentangled 4D Human Generation and Animation from a Single Image},   author={Pang, Hui En and Liu, Shuai and Cai, Zhongang and Yang, Lei and Zhang, Tianwei and Liu, Ziwei},   booktitle={CVPR},   year={2025} }","title":"Disco4D: Disentangled 4D Human Generation and Animation from a Single Image","authors":["Hui En Pang","Shuai Liu","Zhongang Cai","Lei Yang","Tianwei Zhang","Ziwei Liu"],"year":"2025","venue":"CVPR","dataset":false,"survey":false,"bibkey":"pang_disco4d_2024","prior":"FM","inputCondition":"Image","trainingStrategy":"Per-scene","filename":"disco4d.json","thumbnailUrl":"images/disco4d.webp"},{"representation":"Gaussian Splatting","task":"Scene","category":"Video-to-4D","projectPage":"https://hanbyelcho.info/instruct-4dgs/","paperUrl":"https://arxiv.org/abs/2502.02091","codeUrl":"https://github.com/juhyeon-kwon/Instruct-4DGS","tags":["editing"],"motion":"Deformation","codeAvailability":true,"interaction":"","bibtex":"@InProceedings{Kwon_2025_CVPR,     author    = {Kwon, Joohyun and Cho, Hanbyel and Kim, Junmo},     title     = {Efficient Dynamic Scene Editing via 4D Gaussian-based Static-Dynamic Separation},     booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)},     month     = {June},     year      = {2025},     pages     = {26855-26865}     }","title":"Efficient Dynamic Scene Editing via 4D Gaussian-based Static-Dynamic Separation","authors":["Joohyun Kwon","Hanbyel Cho","Junmo Kim"],"year":"2025","venue":"CVPR","dataset":false,"survey":false,"filename":"instruct4dgs.json","thumbnailUrl":"images/instruct4dgs.webp"},{"representation":["Gaussian Splatting"],"task":"Object","category":"Image-to-4D","projectPage":"","paperUrl":"https://arxiv.org/abs/2405.18132v1","codeUrl":"https://github.com/jasongzy/EG4D","tags":[],"motion":["Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{sun2024eg4d,   title={EG4D: Explicit Generation of 4D Object without Score Distillation},   author={Qi Sun and Zhiyang Guo and Ziyu Wan and Jing Nathan Yan and Shengming Yin and Wengang Zhou and Jing Liao and Houqiang Li},   booktitle={ICLR},   year={2025} }","title":"EG4D: Explicit Generation of 4D Object without Score Distillation","authors":["Qi Sun","Zhiyang Guo","Ziyu Wan","Jing Nathan Yan","Shengming Yin","Wengang Zhou","Jing Liao","Houqiang Li"],"year":"2025","venue":"ICLR","dataset":false,"survey":false,"bibkey":"sun_eg4d_2024","prior":"FM","inputCondition":"Image","trainingStrategy":"Per-scene","filename":"eg4d.json","thumbnailUrl":"images/eg4d.webp"},{"title":"FORCE: Dataset and Method for Intuitive Physics Guided Human-object Interaction","authors":["Xiaohan Zhang","Bharat Lal Bhatnagar","Sebastian Starke","Ilya Petrov","Vladimir Guzov","Helisa Dhamo","Eduardo Pérez-Pellitero","Gerard Pons-Moll"],"year":"2025","venue":"3DV","paperUrl":"https://arxiv.org/abs/2403.11237","projectPage":"https://virtualhumans.mpi-inf.mpg.de/force/","codeUrl":"https://github.com/xz6014/FORCE_dataset","representation":["Template"],"motion":["Articulation"],"prior":"TD","inputCondition":"Action+Object","trainingStrategy":"Feed-forward","interactionType":"HOI","task":"Human","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{zhang2025force,\n  title={FORCE: Dataset and Method for Intuitive Physics Guided Human-object Interaction},\n  author={Zhang, Xiaohan and Bhatnagar, Bharat Lal and Starke, Sebastian and Petrov, Ilya and Guzov, Vladimir and Dhamo, Helisa and P{\\'e}rez-Pellitero, Eduardo and Pons-Moll, Gerard},\n  booktitle={3DV},\n  year={2025}\n}","bibkey":"FORCEIntuitivePhysics","filename":"force.json","thumbnailUrl":"images/force.webp"},{"title":"Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videos","authors":["Yingdong Hu","Yisheng He","Jinnan Chen","Weihao Yuan","Kejie Qiu","Zehong Lin","Siyu Zhu","Zilong Dong","Jun Zhang"],"year":"2025","venue":"ArXiv","paperUrl":"https://arxiv.org/abs/2509.24209","projectPage":"https://zhenliuzju.github.io/huyingdong/Forge4D/","codeUrl":"https://github.com/zhenliuZJU/Forge4D","representation":["Gaussian Splatting"],"motion":["Tracking"],"prior":"TD","inputCondition":"Multi-view","trainingStrategy":"Feed-forward","interactionType":"","task":"Human","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@article{forge4d,\n  title={Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videos},\n  author={Yingdong Hu and Yisheng He and Jinnan Chen and Weihao Yuan and Kejie Qiu and Zehong Lin and Siyu Zhu and Zilong Dong and Jun Zhang},\n  journal={arXiv preprint arXiv:2509.24209},\n  year={2025}\n}","filename":"forge4d.json","thumbnailUrl":"images/forge4d.webp"},{"representation":["Gaussian Splatting"],"task":"Scene","category":["Image-to-4D"],"projectPage":"https://free4d.github.io/","paperUrl":"https://arxiv.org/pdf/2503.20785","codeUrl":"https://github.com/TQTQliu/Free4D","tags":[],"motion":["Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@article{liu2025free4d,     title={Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency},     author={Liu, Tianqi and Huang, Zihao and Chen, Zhaoxi and Wang, Guangcong and Hu, Shoukang and Shen, liao and Sun, Huiqiang and Cao, Zhiguo and Li, Wei and Liu, Ziwei},     journal={ICCV},     year={2025} }","title":"Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency","authors":["Tianqi Liu","Zihao Huang","Zhaoxi Chen","Guangcong Wang","Shoukang Hu","liao Shen","Huiqiang Sun","Zhiguo Cao","Wei Li","Ziwei Liu"],"year":"2025","venue":"ICCV","dataset":false,"survey":false,"bibkey":"liu2025free4d","prior":"FM","inputCondition":"Text+Image","trainingStrategy":"Per-scene","filename":"free4d.json","thumbnailUrl":"images/free4d.webp"},{"representation":["Gaussian Splatting"],"task":["Object","Scene"],"category":"Image-to-4D","projectPage":"https://gen-x-d.github.io/","paperUrl":"https://arxiv.org/pdf/2411.02319","codeUrl":"https://github.com/HeliosZhao/GenXD","tags":[],"motion":["Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{zhao2024genxd,   author={Zhao, Yuyang and Lin, Chung-Ching and Lin, Kevin and Yan, Zhiwen and Li, Linjie and Yang, Zhengyuan and Wang, Jianfeng and Lee, Gim Hee and Wang, Lijuan},   title={GenXD: Generating Any 3D and 4D Scenes},   booktitle={ICLR},   year={2025} }","title":"GenXD: Generating Any 3D and 4D Scenes","authors":["Yuyang Zhao","Chung-Ching Lin","Kevin Lin","Zhiwen Yan","Linjie Li","Zhengyuan Yang","Jianfeng Wang","Gim Hee Lee","Lijuan Wang"],"year":"2025","venue":"ICLR","dataset":true,"survey":false,"bibkey":"zhao2024genxd","prior":"FM+TD","inputCondition":"Image","trainingStrategy":"Hybrid","filename":"genxd.json","thumbnailUrl":"images/genxd.webp"},{"representation":["Part","Point Cloud"],"task":"Object","category":"3D-to-4D","projectPage":"","paperUrl":"https://arxiv.org/abs/2504.02747","codeUrl":"","tags":[],"motion":["Articulation"],"codeAvailability":false,"interaction":"","bibtex":"@article{goyal2025geopard,   title={GEOPARD: Geometric Pretraining for Articulation Prediction in 3D Shapes},   author={Goyal, Pradyumn and Petrov, Dmitry and Andrews, Sheldon and Ben-Shabat, Yizhak and Liu, Hsueh-Ti Derek and Kalogerakis, Evangelos},   journal={ICCV},   year={2025} }","title":"GEOPARD: Geometric Pretraining for Articulation Prediction in 3D Shapes","authors":["Pradyumn Goyal","Dmitry Petrov","Sheldon Andrews","Yizhak Ben-Shabat","Hsueh-Ti Derek Liu","Evangelos Kalogerakis"],"year":"2025","venue":"ICCV","dataset":false,"survey":false,"bibkey":"goyal2025geopard","prior":"TD","inputCondition":"Point Cloud","trainingStrategy":"Feed-forward","filename":"geopard.json","thumbnailUrl":"images/geopard.webp"},{"representation":["Gaussian Splatting"],"task":"Object","category":"Image-to-4D","projectPage":"https://in-2-4d.github.io/","paperUrl":"http://arxiv.org/abs/2504.08366","codeUrl":"https://github.com/sauradip/In-2-4D","tags":[],"motion":["Deformation"],"codeAvailability":false,"interaction":"","bibtex":"@article{nag20254din,     title={{In-2-4D}: Inbetweening from Two Single-View Images to 4D Generation},     author = {Nag, Sauradip, Cohen-Or Daniel, Zhang, Hao and Mahdavi-Amiri, Ali},     journal = {SIGGRAPH Asia Conference Papers},     publisher = {ACM New York, NY, USA},     year = {2025},     doi = {https://doi.org/10.1145/3757377.3763904}}","title":"In-2-4D: Inbetweening from Two Single-View Images to 4D Generation","authors":["Sauradip Nag, Daniel Cohen-Or, Hao Zhang","Ali Mahdavi-Amiri"],"year":"2025","venue":"SIGGRAPH Asia","dataset":true,"survey":false,"bibkey":"nag20252","prior":"FM+LLM","inputCondition":"Few-Image","trainingStrategy":"Per-scene","filename":"in24d.json","thumbnailUrl":"images/in24d.webp"},{"representation":["Graph"],"task":"Scene","category":"Video-to-4D","projectPage":"https://sqwu.top/PSG-4D-LLM/","paperUrl":"https://arxiv.org/abs/2503.15019","codeUrl":"https://github.com/ChocoWu/PSG-4D-LLM","tags":[],"motion":["Scene Graph"],"codeAvailability":false,"interaction":"","bibtex":"@inproceedings{wu2025psg4dllm,     title={Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual Scene},     author={Shengqiong Wu and Hao Fei and Jingkang Yang and Xiangtai Li and Juncheng Li and Hanwang Zhang and Tat-Seng Chua1},     booktitle={CVPR},     year={2025} }","title":"Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual Scene","authors":["Shengqiong Wu","Hao Fei","Jingkang Yang","Xiangtai Li","Juncheng Li","Hanwang Zhang","Tat-Seng Chua1"],"year":"2025","venue":"CVPR","bibkey":"wu2025learning","prior":"TD+LLM","inputCondition":"Point Cloud","trainingStrategy":"Feed-forward","filename":"psgllm.json","thumbnailUrl":"images/psgllm.webp"},{"representation":["Mesh"],"task":"Object","category":"3D-to-4D","projectPage":"https://chaoyuesong.github.io/MagicArticulate/","paperUrl":"https://arxiv.org/abs/2502.12135","codeUrl":"https://github.com/Seed3D/MagicArticulate","tags":[],"motion":["Articulation"],"codeAvailability":true,"interaction":"","bibtex":"@InProceedings{Song_2025_CVPR,     author    = {Song, Chaoyue and Zhang, Jianfeng and Li, Xiu and Yang, Fan and Chen, Yiwen and Xu, Zhongcong and Liew, Jun Hao and Guo, Xiaoyang and Liu, Fayao and Feng, Jiashi and Lin, Guosheng},     title     = {MagicArticulate: Make Your 3D Models Articulation-Ready},     booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)},     month     = {June},     year      = {2025},     pages     = {15998-16007} }","title":"MagicArticulate: Make Your 3D Models Articulation-Ready","authors":["Chaoyue Song","Jianfeng Zhang","Xiu Li","Fan Yang","Yiwen Chen","Zhongcong Xu","Jun Hao Liew","Xiaoyang Guo","Fayao Liu","Jiashi Feng","Guosheng Lin"],"year":"2025","venue":"CVPR","dataset":true,"survey":false,"bibkey":"Song_2025_CVPR","prior":"TD","inputCondition":"Mesh","trainingStrategy":"Feed-forward","filename":"magicarticulate.json","thumbnailUrl":"images/magicarticulate.webp"},{"representation":["Part","Mesh"],"task":"Object","category":"3D-to-4D","projectPage":"https://daoyig.github.io/Mesh_Art/","paperUrl":"https://arxiv.org/pdf/2412.11596","codeUrl":"https://github.com/DaoyiG/MeshArt","tags":[],"motion":["Articulation"],"codeAvailability":true,"interaction":"","bibtex":"@InProceedings{gao2025meshart,   title={MeshArt: Generating Articulated Meshes with Structure-guided Transformers},   author={Gao, Daoyi and Siddiqui, Yawar and Li, Lei and Dai, Angela},   booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},   year={2025} } ","title":"MeshArt: Generating Articulated Meshes with Structure-guided Transformers","authors":["Daoyi Gao","Yawar Siddiqui","Lei Li","Angela Dai"],"year":"2025","venue":"CVPR","dataset":true,"survey":false,"bibkey":"gao2025meshart","prior":"TD","inputCondition":"","trainingStrategy":"Feed-forward","filename":"meshart.json","thumbnailUrl":"images/meshart.webp"},{"representation":["Point Cloud"],"task":"Scene","category":"Image-to-4D","projectPage":"https://monst3r-project.github.io/","paperUrl":"https://arxiv.org/abs/2410.03825","codeUrl":"https://github.com/Junyi42/monst3r","tags":[],"motion":["Per frame","Tracking"],"codeAvailability":true,"interaction":"","bibtex":"@article{zhang2024monst3r,   title={Monst3r: A simple approach for estimating geometry in the presence of motion},   author={Zhang, Junyi and Herrmann, Charles and Hur, Junhwa and Jampani, Varun and Darrell, Trevor and Cole, Forrester and Sun, Deqing and Yang, Ming-Hsuan},   journal={ICLR},   year={2025} }","title":"Monst3r: A simple approach for estimating geometry in the presence of motion","authors":["Junyi Zhang","Charles Herrmann","Junhwa Hur","Varun Jampani","Trevor Darrell","Forrester Cole","Deqing Sun","Ming-Hsuan Yang"],"year":"2025","venue":"ICLR","dataset":false,"survey":false,"bibkey":"zhang2024monst3r","prior":"TD","inputCondition":"Video","trainingStrategy":"Feed-forward","filename":"monst3r.json","thumbnailUrl":"images/monst3r.webp"},{"representation":["Gaussian Splatting"],"task":"Scene","category":"Video-to-4D","projectPage":"https://jiahuilei.com/projects/mosca/","paperUrl":"https://www.cis.upenn.edu/~leijh/projects/mosca/pub/mosca_v2.pdf","codeUrl":"https://github.com/JiahuiLei/MoSca","tags":[],"motion":["Deformation","Tracking"],"codeAvailability":true,"interaction":"","bibtex":"@article{lei2024mosca, title={MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds}, author={Lei, Jiahui and Weng, Yijia and Harley, Adam and Guibas, Leonidas and Daniilidis, Kostas}, journal={CVPR}, year={2025} }","title":"MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds","authors":["Jiahui Lei","Yijia Weng","Adam Harley","Leonidas Guibas","Kostas Daniilidis"],"year":"2025","venue":"CVPR","dataset":false,"survey":false,"bibkey":"lei2024mosca","prior":"Input","inputCondition":"Video","trainingStrategy":"Per-scene","filename":"mosca.json","thumbnailUrl":"images/mosca.webp"},{"representation":"Template","task":"Human","category":"3D-to-4D","projectPage":"https://motiondreamer.github.io/","paperUrl":"https://arxiv.org/abs/2504.08959","codeUrl":"https://github.com/MotionDreamer/MotionDreamer","tags":[],"motion":"Articulation","codeAvailability":false,"interaction":"","bibtex":"@inproceedings{ wang2025motiondreamer, title={MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer}, author={Yilin Wang and chuan guo and Yuxuan Mu and Muhammad Gohar Javed and Xinxin Zuo and Juwei Lu and Hai Jiang and Li cheng}, booktitle={The Thirteenth International Conference on Learning Representations}, year={2025}, url={https://openreview.net/forum?id=d23EVDRJ6g} }","title":"MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer","authors":["Yilin Wang","chuan guo","Yuxuan Mu","Muhammad Gohar Javed","Xinxin Zuo","Juwei Lu","Hai Jiang","Li cheng"],"year":"2025","venue":"ICLR","filename":"motiondreamer.json","thumbnailUrl":"images/motiondreamer.webp"},{"representation":["Template","Gaussian Splatting"],"task":"Object","category":"Image-to-4D","projectPage":"https://felixtaubner.github.io/mvp4d/","paperUrl":"http://arxiv.org/abs/2510.12785","codeUrl":"https://github.com/felixtaubner/mvp4d/","tags":[],"motion":["Articulation","Deformation"],"codeAvailability":false,"interaction":"","bibtex":" @article{taubner2025mvp4d,   title={MVP4D: Multi-View Portrait Video Diffusion for Animatable {4D} Avatars},    author={Felix Taubner and Ruihang Zhang and Mathieu Tuli and Sherwin Bahmani and David B. Lindell},   year={2025},   eprint={2510.12785},   archivePrefix={Siggraph},   primaryClass={cs.CV},   url={https://arxiv.org/abs/2510.12785},  }","title":"MVP4D: Multi-View Portrait Video Diffusion for Animatable {4D","authors":["Felix Taubner","Ruihang Zhang","Mathieu Tuli","Sherwin Bahmani","David B. Lindell"],"year":"2025","venue":"SIGGRAPH Asia","dataset":false,"survey":false,"bibkey":"taubner2025mvp4d","prior":"FM+TD","inputCondition":"Image","trainingStrategy":"Hybrid","filename":"mvp4d.json","thumbnailUrl":"images/mvp4d.webp"},{"representation":["Gaussian Splatting"],"task":"Object","category":"Video-to-4D","projectPage":"https://soolab.github.io/MVTokenFlow/","paperUrl":"https://arxiv.org/abs/2502.11697","codeUrl":"https://github.com/SooLab/MVTokenFlow","tags":[],"motion":["Deformation","Tracking"],"codeAvailability":false,"interaction":"","bibtex":"@article{huang2025mvtokenflow,   title={MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow},   author={Huang, Hanzhuo and Liu, Yuan and Zheng, Ge and Wang, Jiepeng and Dou, Zhiyang and Yang, Sibei},   journal={ICLR},   year={2025} }","title":"MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow","authors":["Hanzhuo Huang","Yuan Liu","Ge Zheng","Jiepeng Wang","Zhiyang Dou","Sibei Yang"],"year":"2025","venue":"ICLR","dataset":false,"survey":false,"bibkey":"huang2025mvtokenflow","prior":"FM","inputCondition":"Video","trainingStrategy":"Per-scene","filename":"mvtokenflow.json","thumbnailUrl":"images/mvtokenflow.webp"},{"title":"PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos","authors":["Hanxiao Jiang","Hao-Yu Hsu","Kaifeng Zhang","Hsin-Ni Yu","Shenlong Wang","Yunzhu Li"],"year":"2025","venue":"ICCV","paperUrl":"https://arxiv.org/abs/2503.17973","projectPage":"https://jianghanxiao.github.io/phystwin-web/","codeUrl":"https://github.com/Jianghanxiao/PhysTwin","representation":["Gaussian Splatting","Point Cloud"],"task":["Object","Hand"],"category":["Video-to-4D","4D understanding"],"motion":["Deformation"],"interaction":"Human-Object Interaction","codeAvailability":true,"bibtex":"@article{jiang2025phystwin, title={PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos}, author={Jiang, Hanxiao and Hsu, Hao-Yu and Zhang, Kaifeng and Yu, Hsin-Ni and Wang, Shenlong and Li, Yunzhu}, journal={ICCV}, year={2025} }","dataset":false,"survey":false,"filename":"phystwin.json","thumbnailUrl":"images/phystwin.webp"},{"representation":["Mesh"],"task":"Object","category":["3D-to-4D","Text-to-4D"],"projectPage":"https://chaoyuesong.github.io/Puppeteer/","paperUrl":"https://arxiv.org/pdf/2508.10898","codeUrl":"https://github.com/Seed3D/Puppeteer","tags":[],"motion":["Articulation"],"codeAvailability":true,"interaction":"","bibtex":"@article{song2025puppeteer,         title={Puppeteer: Rig and Animate Your 3D Models},         author={Chaoyue Song and Xiu Li and Fan Yang and Zhongcong Xu and Jiacheng Wei and Fayao Liu and Jiashi Feng and Guosheng Lin and Jianfeng Zhang},         journal={Advances in Neural Information Processing Systems},         year={2025}       }","title":"Puppeteer: Rig and Animate Your 3D Models","authors":["Chaoyue Song","Xiu Li","Fan Yang","Zhongcong Xu","Jiacheng Wei","Fayao Liu","Jiashi Feng","Guosheng Lin","Jianfeng Zhang"],"year":"2025","venue":"NeurIPS","dataset":false,"survey":false,"bibkey":"song2025puppeteer","prior":"FM+TD","inputCondition":"Text/Mesh","trainingStrategy":"Hybrid","filename":"puppeteer.json","thumbnailUrl":"images/puppeteer.webp"},{"representation":"","task":"","category":[],"projectPage":"https://github.com/yukangcao/Awesome-4D-Spatial-Intelligence","paperUrl":"https://arxiv.org/pdf/2507.21045","codeUrl":"","tags":[],"motion":"","codeAvailability":false,"interaction":"","bibtex":"@article{cao2025reconstructing,  title={Reconstructing 4D Spatial Intelligence: A Survey},  author={Cao, Yukang and Lu, Jiahao and Huang, Zhisheng and Shen, Zhuowen and Zhao, Chengfeng and Hong, Fangzhou and Chen, Zhaoxi and Li, Xin and Wang, Wenping and Liu, Yuan and others},  journal={ArXiv},  year={2025}}","title":"Reconstructing 4D Spatial Intelligence: A Survey","authors":["Yukang Cao","Jiahao Lu","Zhisheng Huang","Zhuowen Shen","Chengfeng Zhao","Fangzhou Hong","Zhaoxi Chen","Xin Li","Wenping Wang","Yuan Liu","Ziwei Liu"],"year":"2025","venue":"ArXiv","dataset":false,"survey":true,"filename":"4dSI.json","thumbnailUrl":"images/4dSI.webp"},{"title":"Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions","authors":["Boran Wen","Dingbang Huang","Zichen Zhang","Jiahong Zhou","Jianbin Deng","Jingyu Gong","Yulong Chen","Lizhuang Ma","Yong-Lu Li"],"year":"2025","venue":"CVPR","paperUrl":"https://arxiv.org/abs/2503.15898","projectPage":"https://wenboran2002.github.io/3dhoi/","codeUrl":"https://github.com/wenboran2002/open-3dhoi","representation":["Template","Gaussian Splatting"],"motion":["Articulation"],"prior":"FM+Human","inputCondition":"Image","trainingStrategy":"Per-scene","interactionType":"HOI","task":"Human","category":[],"tags":[],"interaction":"","codeAvailability":false,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{wen2025reconstructing,\n  title={Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions},\n  author={Wen, Boran and Huang, Dingbang and Zhang, Zichen and Zhou, Jiahong and Deng, Jianbin and Gong, Jingyu and Chen, Yulong and Ma, Lizhuang and Li, Yong-Lu},\n  booktitle={CVPR},\n  year={2025}\n}","bibkey":"wen2025reconstructing","filename":"open3dhoi.json","thumbnailUrl":"images/open3dhoi.webp"},{"representation":["Mesh"],"task":"Object","category":"3D-to-4D","projectPage":"https://www.liuisabella.com/RigAnything/","paperUrl":"https://arxiv.org/abs/2502.09615","codeUrl":"https://github.com/Isabella98Liu/RigAnything","tags":[],"motion":["Articulation"],"codeAvailability":true,"interaction":"","bibtex":"@article{liu2025riganything,   title={Riganything: Template-free autoregressive rigging for diverse 3d assets},   author={Liu, Isabella and Xu, Zhan and Yifan, Wang and Tan, Hao and Xu, Zexiang and Wang, Xiaolong and Su, Hao and Shi, Zifan},   journal={ACM Transactions on Graphics (TOG)},   volume={44},   number={4},   pages={1--12},   year={2025},   publisher={ACM New York, NY, USA} }","title":"Riganything: Template-free autoregressive rigging for diverse 3d assets","authors":["Isabella Liu","Zhan Xu","Wang Yifan","Hao Tan","Zexiang Xu","Xiaolong Wang","Hao Su","Zifan Shi"],"year":"2025","venue":"ACM TOG","dataset":false,"survey":false,"bibkey":"liu2025riganything","prior":"TD","inputCondition":"Mesh","trainingStrategy":"Feed-forward","filename":"riganything.json","thumbnailUrl":"images/riganything.webp"},{"representation":["Part","Graph","Mesh"],"task":"Object","category":"Image-to-4D","projectPage":"https://3dlg-hcvc.github.io/singapo/","paperUrl":"https://arxiv.org/pdf/2410.16499","codeUrl":"https://github.com/3dlg-hcvc/singapo","tags":[],"motion":["Articulation"],"codeAvailability":true,"interaction":"","bibtex":"@article{jiayi2025singapo,           author    = {Liu, Jiayi and Iliash, Denys and Chang, Angel X. and Savva, Manolis and Mahdavi-Amiri, Ali},           title     = {SINGAPO: Single Image Controlled Generation of Articulated Parts in Object},           year      = {2025},           journal   = {ICLR}       }","title":"SINGAPO: Single Image Controlled Generation of Articulated Parts in Object","authors":["Jiayi Liu","Denys Iliash","Angel X. Chang","Manolis Savva","Ali Mahdavi-Amiri"],"year":"2025","venue":"ICLR","dataset":false,"survey":false,"bibkey":"liu2024singapo","prior":"TD+LLM","inputCondition":"Image","trainingStrategy":"Feed-forward","filename":"singapo.json","thumbnailUrl":"images/singapo.webp"},{"representation":["Point Cloud"],"task":"Scene","category":"Video-to-4D","projectPage":"https://st4rtrack.github.io/","paperUrl":"https://arxiv.org/abs/2504.13152","codeUrl":"https://github.com/HavenFeng/St4RTrack","tags":[],"motion":["Tracking"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{st4rtrack2025,     title={St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World},<br>     author={Feng*, Haiwen and Zhang*, Junyi and Wang, Qianqian and Ye, Yufei and Yu, Pengcheng and Black, Michael J. and Darrell, Trevor and Kanazawa, Angjoo},<br>     booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},<br>     year={2025} }","title":"St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World","authors":["Haiwen Feng*","Junyi Zhang*","Qianqian Wang","Yufei Ye","Pengcheng Yu","Michael J. Black","Trevor Darrell","Angjoo Kanazawa"],"year":"2025","venue":"ICCV","dataset":false,"survey":false,"bibkey":"feng2025st4rtrack","prior":"TD","inputCondition":"Video","trainingStrategy":"Feed-forward","filename":"st4rtrack.json","thumbnailUrl":"images/st4rtrack.webp"},{"representation":["Part","Mesh"],"task":"Object","category":"Video-to-4D","projectPage":"https://stablepartdiffusion4d.github.io/","paperUrl":"https://arxiv.org/abs/2509.10687","codeUrl":"https://github.com/Stability-AI/generative-models/tree/sp4d","tags":[],"motion":["Articulation"],"codeAvailability":true,"interaction":"","bibtex":"@article{zhang2025stable,   title={Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation},   author={Zhang, Hao and Yao, Chun-Han and Donne, Simon and Ahuja, Narendra and Jampani, Varun},   journal={NeurIPS},   year={2025} }","title":"Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation","authors":["Hao Zhang","Chun-Han Yao","Simon Donne","Narendra Ahuja","Varun Jampani"],"year":"2025","venue":"NeurIPS","dataset":false,"survey":false,"bibkey":"zhang2025sp4d","prior":"FM+TD","inputCondition":"Video","trainingStrategy":"Hybrid","filename":"sp4d.json","thumbnailUrl":"images/sp4d.webp"},{"representation":"NeRF","task":["Object","Scene"],"category":["Video-to-4D"],"projectPage":"https://sv4d20.github.io/","paperUrl":"https://arxiv.org/pdf/2503.16396","codeUrl":"https://github.com/Stability-AI/generative-models","tags":[],"motion":"Deformation","codeAvailability":true,"interaction":"","bibtex":"@article{yao2024sv4d2,    title={{SV4D2.0}: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation},     author={Chun-Han Yao and Yiming Xie and Vikram Voleti and Huaizu Jiang and Varun Jampani},    journal={ICCV},    year={2025},}","title":"SV4D2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation","authors":["Chun-Han Yao","Yiming Xie","Vikram Voleti","Huaizu Jiang","Varun Jampani"],"year":"2025","venue":"ICCV","dataset":false,"survey":false,"filename":"sv4d2.json","thumbnailUrl":"images/sv4d2.webp"},{"representation":["NeRF"],"task":"Object","category":["Video-to-4D"],"projectPage":"https://sv4d.github.io/","paperUrl":"https://arxiv.org/abs/2407.17470","codeUrl":"https://github.com/Stability-AI/generative-models","tags":[],"motion":["Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@article{xie2024sv4d, title={Sv4d: Dynamic 3d content generation with multi-frame and multi-view consistency}, author={Xie, Yiming and Yao, Chun-Han and Voleti, Vikram and Jiang, Huaizu and Jampani, Varun}, journal={ICLR}, year={2025} } year = {2023}, pages = {21128-21137} }","title":"Sv4d: Dynamic 3d content generation with multi-frame and multi-view consistency","authors":["Yiming Xie","Chun-Han Yao","Vikram Voleti","Huaizu Jiang","Varun Jampani"],"year":"2025","venue":"ICLR","dataset":false,"survey":false,"bibkey":"xie_sv4d_2024","prior":"FM+TD","inputCondition":"Video","trainingStrategy":"Hybrid","filename":"sv4d.json","thumbnailUrl":"images/sv4d.webp"},{"representation":["Mesh"],"task":"Object","category":["Text-to-4D"],"projectPage":"","paperUrl":"https://arxiv.org/abs/2506.24121","codeUrl":"","tags":[],"motion":["Deformation"],"codeAvailability":false,"interaction":"","bibtex":"@article{TextMesh4D,title={TextMesh4D: High-Quality Text-to-4D Mesh Generation},author={Dai, Sisi and Su, Xinxin and Wan, Boyan and Hu, Ruizhen and Xu, Kai},journal={ArXiv},year={2025}}","title":"TextMesh4D: High-Quality Text-to-4D Mesh Generation","authors":["Sisi Dai","Xinxin Su","Boyan Wan","Ruizhen Hu","Kai Xu"],"year":"2025","venue":"ArXiv","dataset":false,"survey":false,"bibkey":"TextMesh4D","prior":"FM","inputCondition":"Text","trainingStrategy":"Per-scene","filename":"textmesh4d.json","thumbnailUrl":"images/textmesh4d.webp"},{"representation":["Mesh"],"task":"Object","category":["Video-to-4D"],"projectPage":"https://windvchen.github.io/V2M4/","paperUrl":"https://arxiv.org/pdf/2503.09631","codeUrl":"https://github.com/WindVChen/V2M4","tags":[],"motion":["Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{chen2025v2m4, title={V2M4: 4D Mesh Animation Reconstruction from a Single Monocular Video}, author={Chen, Jianqi and Zhang, Biao and Tang, Xiangjun and Wonka, Peter}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year={2025} }","title":"V2M4: 4D Mesh Animation Reconstruction from a Single Monocular Video","authors":["Jianqi Chen","Biao Zhang","Xiangjun Tang","Peter Wonka"],"year":"2025","venue":"ICCV","dataset":false,"survey":false,"bibkey":"chen2025v2m4","prior":"FM","inputCondition":"Video","trainingStrategy":"Per-scene","filename":"v2m4.json","thumbnailUrl":"images/v2m4.webp"},{"representation":["Gaussian Splatting"],"task":"Scene","category":"Video-to-4D","projectPage":"https://guanjunwu.github.io/4dgs/","paperUrl":"https://arxiv.org/abs/2310.08528","codeUrl":"https://github.com/hustvl/4DGaussians","tags":[],"motion":["Space-Time","Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@InProceedings{Wu_2024_CVPR,                         author    = {Wu, Guanjun and Yi, Taoran and Fang, Jiemin and Xie, Lingxi and Zhang, Xiaopeng and Wei, Wei and Liu, Wenyu and Tian, Qi and Wang, Xinggang},                         title     = {4D Gaussian Splatting for Real-Time Dynamic Scene Rendering},                         booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},                         month     = {June},                         year      = {2024},                         pages     = {20310-20320}                     }","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","authors":["Guanjun Wu","Taoran Yi","Jiemin Fang","Lingxi Xie","Xiaopeng Zhang","Wei Wei","Wenyu Liu","Qi Tian","Xinggang Wang"],"year":"2024","venue":"CVPR","dataset":false,"survey":false,"bibkey":"Wu_2024_CVPR","prior":"Input","inputCondition":"Video","trainingStrategy":"Per-scene","filename":"4dgs.json","thumbnailUrl":"images/4dgs.webp"},{"representation":["NeRF"],"task":"Scene","category":["Text-to-4D"],"projectPage":"https://sherwinbahmani.github.io/4dfy/","paperUrl":"https://arxiv.org/abs/2311.17984","codeUrl":"https://github.com/sherwinbahmani/4dfy","tags":[],"motion":["Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@article{bah20244dfy,  author = {Bahmani, Sherwin and Skorokhodov, Ivan and Rong, Victor and Wetzstein, Gordon and Guibas, Leonidas and Wonka, Peter and Tulyakov, Sergey and Park, Jeong Joon and Tagliasacchi, Andrea and Lindell, David B.},  title = {4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling},  journal = {IEEE Conference on Computer Vision and Pattern Recognition ({CVPR})},  year = {2024},}","title":"4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling","authors":["Sherwin Bahmani","Ivan Skorokhodov","Victor Rong","Gordon Wetzstein","Leonidas Guibas","Peter Wonka","Sergey Tulyakov","Jeong Joon Park","Andrea Tagliasacchi","David B. Lindell"],"year":"2024","venue":"CVPR","dataset":false,"survey":false,"bibkey":"bahmani20244dfy","prior":"FM","inputCondition":"Text","trainingStrategy":"Per-scene","filename":"4d-fy.json","thumbnailUrl":"images/4d-fy.webp"},{"representation":["Gaussian Splatting"],"task":"Scene","category":"Video-to-4D","projectPage":"https://weify627.github.io/4drotorgs/","paperUrl":"https://arxiv.org/abs/2402.03307","codeUrl":"https://github.com/weify627/4D-Rotor-Gaussians","tags":[],"motion":["Space-Time"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{duan20244d,   title={4d-rotor gaussian splatting: towards efficient novel view synthesis for dynamic scenes},   author={Duan, Yuanxing and Wei, Fangyin and Dai, Qiyu and He, Yuhang and Chen, Wenzheng and Chen, Baoquan},   booktitle={ACM SIGGRAPH 2024 Conference Papers},   pages={1--11},   year={2024} }","title":"4d-rotor gaussian splatting: towards efficient novel view synthesis for dynamic scenes","authors":["Yuanxing Duan","Fangyin Wei","Qiyu Dai","Yuhang He","Wenzheng Chen","Baoquan Chen"],"year":"2024","venue":"SIGGRAPH","dataset":false,"survey":false,"bibkey":"duan20244d","prior":"Input","inputCondition":"Video","trainingStrategy":"Per-scene","filename":"4drotor.json","thumbnailUrl":"images/4drotor.webp"},{"representation":["NeRF"],"task":"Object","category":["Video-to-4D"],"projectPage":"https://aejion.github.io/4diffusion/","paperUrl":"http://arxiv.org/abs/2405.20674","codeUrl":"https://github.com/aejion/4Diffusion","tags":[],"motion":["Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@article{zhang20244diffusion,   title={4diffusion: Multi-view video diffusion model for 4d generation},   author={Zhang, Haiyu and Chen, Xinyuan and Wang, Yaohui and Liu, Xihui and Wang, Yunhong and Qiao, Yu},   journal={Advances in Neural Information Processing Systems},   volume={37},   pages={15272--15295},   year={2024} }","title":"4diffusion: Multi-view video diffusion model for 4d generation","authors":["Haiyu Zhang","Xinyuan Chen","Yaohui Wang","Xihui Liu","Yunhong Wang","Yu Qiao"],"year":"2024","venue":"NeurIPS","dataset":false,"survey":false,"bibkey":"zhang_4diffusion_2024","prior":"FM+TD","inputCondition":"Video","trainingStrategy":"Hybrid","filename":"4diffusion.json","thumbnailUrl":"images/4diffusion.webp"},{"representation":["Gaussian Splatting"],"task":"Scene","category":["Text-to-4D","Video-to-4D"],"projectPage":"https://snap-research.github.io/4Real/","paperUrl":"https://arxiv.org/abs/2406.07472","codeUrl":"","tags":[],"motion":["Deformation"],"codeAvailability":false,"interaction":"","bibtex":"@article{yu20244real,   title={4real: Towards photorealistic 4d scene generation via video diffusion models},   author={Yu, Heng and Wang, Chaoyang and Zhuang, Peiye and Menapace, Willi and Siarohin, Aliaksandr and Cao, Junli and Jeni, Laszlo and Tulyakov, Sergey and Lee, Hsin-Ying},   journal={Advances in Neural Information Processing Systems},   volume={37},   pages={45256--45280},   year={2024} }","title":"4real: Towards photorealistic 4d scene generation via video diffusion models","authors":["Heng Yu","Chaoyang Wang","Peiye Zhuang","Willi Menapace","Aliaksandr Siarohin","Junli Cao","Laszlo Jeni","Sergey Tulyakov","Hsin-Ying Lee"],"year":"2024","venue":"NeurIPS","dataset":false,"survey":false,"bibkey":"yu_4real_2024","prior":"FM","inputCondition":"Text","trainingStrategy":"Per-scene","filename":"4real.json","thumbnailUrl":"images/4real.webp"},{"title":"AffordanceLLM: Grounding Affordance from Vision Language Models","authors":["Shengyi Qian","Weifeng Chen","Min Bai","Xiong Zhou","Zhuowen Tu","Li Erran Li"],"year":"2024","venue":"CVPR Workshops","paperUrl":"https://arxiv.org/abs/2401.06341","projectPage":"https://jasonqsy.github.io/AffordanceLLM/","codeUrl":"","representation":["Image"],"motion":[],"prior":"TD+LLM","inputCondition":"Text+Image","trainingStrategy":"Feed-forward","interactionType":"Affordance prediction","task":"Object","category":[],"tags":[],"interaction":"","codeAvailability":false,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{qian2024affordancellm,\n  title={AffordanceLLM: Grounding Affordance from Vision Language Models},\n  author={Qian, Shengyi and Chen, Weifeng and Bai, Min and Zhou, Xiong and Tu, Zhuowen and Li, Li Erran},\n  booktitle={CVPR Workshops},\n  year={2024}\n}","bibkey":"AffordanceLLM","filename":"affordancellm.json","thumbnailUrl":"images/affordancellm.webp"},{"representation":"Gaussian Splatting","task":"Scene","category":["Text-to-4D"],"projectPage":"https://research.nvidia.com/labs/toronto-ai/AlignYourGaussians/","paperUrl":"https://arxiv.org/abs/2312.13763","codeUrl":"","tags":[],"motion":"Deformation","codeAvailability":false,"interaction":"","bibtex":"@inproceedings{ling2024alignyourgaussians,    title={Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models},    author={Ling, Huan and Kim, Seung Wook and Torralba, Antonio and Fidler, Sanja and Kreis, Karsten},    booktitle={CVPR})},    year={2024}}","title":"Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models","authors":["Huan Ling","Seung Wook Kim","Antonio Torralba","Sanja Fidler","Karsten Kreis"],"year":"2024","venue":"CVPR","dataset":false,"survey":false,"filename":"ayg.json","thumbnailUrl":"images/ayg.webp"},{"representation":"NeRF","task":"Object","category":["Video-to-4D"],"projectPage":"https://zz7379.github.io/AnimatableDreamer/","paperUrl":"https://arxiv.org/abs/2312.03795","codeUrl":"","tags":[],"motion":["Articulation"],"codeAvailability":false,"interaction":"","bibtex":"@inproceedings{wang2024animatabledreamer,  title={Animatabledreamer: Text-guided non-rigid 3d model generation and reconstruction with canonical score distillation},  author={Wang, Xinzhou and Wang, Yikai and Ye, Junliang and Sun, Fuchun and Wang, Zhengyi and Wang, Ling and Liu, Pengkun and Sun, Kai and Wang, Xintong and Xie, Wende and others},  booktitle={ECCV},  pages={321--339},  year={2024},  organization={Springer}}","title":"Animatabledreamer: Text-guided non-rigid 3d model generation and reconstruction with canonical score distillation","authors":["Xinzhou Wang","Yikai Wang","Junliang Ye","Fuchun Sun","Zhengyi Wang","Ling Wang","Pengkun Liu","Kai Sun","Xintong Wang","Wende Xie","others"],"year":"2024","venue":"ECCV","dataset":false,"survey":false,"filename":"animatabledreamer.json","thumbnailUrl":"images/animatabledreamer.webp"},{"representation":["NeRF"],"task":"Scene","category":["Image-to-4D"],"projectPage":"https://animate124.github.io/","paperUrl":"https://arxiv.org/pdf/2311.14603","codeUrl":"https://github.com/HeliosZhao/Animate124","tags":[],"motion":["Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@article{zhao2023animate124,  author    = {Zhao, Yuyang and Yan, Zhiwen and Xie, Enze and Hong, Lanqing and Li, Zhenguo and Lee, Gim Hee},  title     = {Animate124: Animating One Image to 4D Dynamic Scene},  journal   = {ArXiv},  year      = {2024},}","title":"Animate124: Animating One Image to 4D Dynamic Scene","authors":["Yuyang Zhao","Zhiwen Yan","Enze Xie","Lanqing Hong","Zhenguo Li","Gim Hee Lee"],"year":"2024","venue":"ArXiv","dataset":false,"survey":false,"bibkey":"zhao2023animate124","prior":"FM","inputCondition":"Text+Image","trainingStrategy":"Per-scene","filename":"animate124.json","thumbnailUrl":"images/animate124.webp"},{"representation":["Gaussian Splatting"],"task":"Object","category":"3D-to-4D","projectPage":"https://animate3d.github.io/","paperUrl":"https://arxiv.org/abs/2407.11398","codeUrl":"https://github.com/yanqinJiang/Animate3D","tags":[],"motion":"Deformation","codeAvailability":true,"interaction":"","bibtex":"@article{jiang2024animate3d,   title={Animate3d: Animating any 3d model with multi-view video diffusion},   author={Jiang, Yanqin and Yu, Chaohui and Cao, Chenjie and Wang, Fan and Hu, Weiming and Gao, Jin},   journal={Advances in Neural Information Processing Systems},   volume={37},   pages={125879--125906},   year={2024} }","title":"Animate3d: Animating any 3d model with multi-view video diffusion","authors":["Yanqin Jiang","Chaohui Yu","Chenjie Cao","Fan Wang","Weiming Hu","Jin Gao"],"year":"2024","venue":"NeurIPS","dataset":true,"survey":false,"filename":"animate3d.json","thumbnailUrl":"images/animate3d.webp"},{"title":"CG-HOI: Contact-Guided 3D Human-Object Interaction Generation","authors":["Christian Diller","Angela Dai"],"year":"2024","venue":"CVPR","paperUrl":"https://arxiv.org/abs/2311.16097","projectPage":"https://www.christian-diller.de/projects/cg-hoi/","codeUrl":"","representation":["Template","Mesh"],"motion":["Articulation"],"prior":"TD","inputCondition":"Text","trainingStrategy":"Feed-forward","interactionType":"HOI","task":"Human","category":[],"tags":[],"interaction":"","codeAvailability":false,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{cghoi,\n  title={CG-HOI: Contact-Guided 3D Human-Object Interaction Generation},\n  author={Christian Diller and Angela Dai},\n  booktitle={CVPR},\n  year={2024}\n}","filename":"cghoi.json","thumbnailUrl":"images/cghoi.webp"},{"representation":["NeRF"],"task":"Object","category":["Video-to-4D"],"projectPage":"https://consistent4d.github.io/","paperUrl":"https://arxiv.org/abs/2311.02848","codeUrl":"https://github.com/yanqinJiang/Consistent4D","tags":["Dataset"],"motion":["Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{ jiang2024consistentd, title={Consistent4D: Consistent 360 degree Dynamic Object Generation from Monocular Video}, author={Yanqin Jiang and Li Zhang and Jin Gao and Weiming Hu and Yao Yao}, booktitle={The Twelfth International Conference on Learning Representations}, year={2024}, url={https://openreview.net/forum?id=sPUrdFGepF} }","title":"Consistent4D: Consistent 360 degree Dynamic Object Generation from Monocular Video","authors":["Yanqin Jiang","Li Zhang","Jin Gao","Weiming Hu","Yao Yao"],"year":"2024","venue":"ICLR","dataset":true,"survey":false,"bibkey":"jiang2023consistent4d","prior":"FM+TD","inputCondition":"Video","trainingStrategy":"Per-scene","filename":"consistent4D.json","thumbnailUrl":"images/consistent4D.webp"},{"representation":["Gaussian Splatting"],"task":"Object","category":["Text-to-4D","Image-to-4D","3D-to-4D"],"projectPage":"https://vita-group.github.io/Diffusion4D/","paperUrl":"https://arxiv.org/abs/2405.16645","codeUrl":"https://github.com/VITA-Group/Diffusion4D","tags":[],"motion":"Deformation","codeAvailability":true,"interaction":"","bibtex":"@article{liang2024diffusion4d,   title={Diffusion4d: Fast spatial-temporal consistent 4d generation via video diffusion models},   author={Liang, Hanwen and Yin, Yuyang and Xu, Dejia and Liang, Hanxue and Wang, Zhangyang and Plataniotis, Konstantinos N and Zhao, Yao and Wei, Yunchao},   journal={NeurIPS},   year={2024} }","title":"Diffusion4d: Fast spatial-temporal consistent 4d generation via video diffusion models","authors":["Hanwen Liang","Yuyang Yin","Dejia Xu","Hanxue Liang","Zhangyang Wang","Konstantinos N Plataniotis","Yao Zhao","Yunchao Wei"],"year":"2024","venue":"NeurIPS","dataset":true,"survey":false,"filename":"diffusion4d.json","thumbnailUrl":"images/diffusion4d.webp"},{"representation":["NeRF"],"task":["Object","Scene"],"category":["Image-to-4D","Text-to-4D"],"projectPage":"https://research.nvidia.com/labs/nxp/dream-in-4d/","paperUrl":"https://arxiv.org/abs/2311.16854","codeUrl":"https://github.com/NVlabs/dream-in-4d","tags":[],"motion":["Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@InProceedings{zheng2024unified,title = {Dream in 4D:A Unified Approach for Text- and Image-guided 4D Scene Generation},author    = {Yufeng Zheng and Xueting Li and Koki Nagano and Sifei Liu and Otmar Hilliges and Shalini De Mello},booktitle = {CVPR},year      = {2024}}","title":"Dream in 4D:A Unified Approach for Text- and Image-guided 4D Scene Generation","authors":["Yufeng Zheng","Xueting Li","Koki Nagano","Sifei Liu","Otmar Hilliges","Shalini De Mello"],"year":"2024","venue":"CVPR","dataset":false,"survey":false,"bibkey":"zheng_unified_2024","prior":"FM","inputCondition":"Text/Image","trainingStrategy":"Per-scene","filename":"dream-in-4d.json","thumbnailUrl":"images/dream-in-4d.webp"},{"representation":["Mesh","Gaussian Splatting"],"task":"Object","category":["Video-to-4D"],"projectPage":"https://lizhiqi49.github.io/DreamMesh4D/","paperUrl":"https://arxiv.org/abs/2410.06756","codeUrl":"https://github.com/WU-CVGL/DreamMesh4D","tags":[],"motion":["Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{li2024dreammesh4d,        title={DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation},        author={Zhiqi Li and Yiming Chen and Peidong Liu},        booktitle={NeurIPS},        year={2024}    }","title":"DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation","authors":["Zhiqi Li","Yiming Chen","Peidong Liu"],"year":"2024","venue":"NeurIPS","dataset":false,"survey":false,"bibkey":"li2024dreammesh4d","prior":"FM","inputCondition":"Video","trainingStrategy":"Per-scene","filename":"dreammesh4d.json","thumbnailUrl":"images/dreammesh4d.webp"},{"title":"DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos","authors":["Wen-Hsuan Chu","Lei Ke","Katerina Fragkiadaki"],"year":"2024","venue":"NeurIPS","paperUrl":"https://arxiv.org/abs/2405.02280","projectPage":"https://dreamscene4d.github.io/","codeUrl":"https://github.com/dreamscene4d/dreamscene4d","representation":["Gaussian Splatting"],"motion":["Deformation","Tracking"],"prior":"FM","inputCondition":"Video","trainingStrategy":"Per-scene","interactionType":"","task":"Scene","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{dreamscene4d,\n  title={DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos},\n  author={Wen-Hsuan Chu and Lei Ke and Katerina Fragkiadaki},\n  booktitle={NeurIPS},\n  year={2024}\n}","filename":"dreamscene4d.json","thumbnailUrl":"images/dreamscene4d.webp"},{"representation":["Gaussian Splatting"],"task":"Scene","category":"Video-to-4D","projectPage":"https://dynamic3dgaussians.github.io/","paperUrl":"https://arxiv.org/pdf/2308.09713.pdf","codeUrl":"https://github.com/JonathonLuiten/Dynamic3DGaussians","tags":[],"motion":["Space-Time","Tracking"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{luiten2023dynamic,   title={Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis},   author={Luiten, Jonathon and Kopanas, Georgios and Leibe, Bastian and Ramanan, Deva},   booktitle={3DV},   year={2024} }","title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis","authors":["Jonathon Luiten","Georgios Kopanas","Bastian Leibe","Deva Ramanan"],"year":"2024","venue":"3DV","dataset":false,"survey":false,"bibkey":"luiten2024dynamic","prior":"Input","inputCondition":"Video","trainingStrategy":"Per-scene","filename":"dyn3dgs.json","thumbnailUrl":"images/dyn3dgs.webp"},{"representation":["Gaussian Splatting"],"task":"Scene","category":"Video-to-4D","projectPage":"https://geometry.stanford.edu/projects/dynamic-gaussian-marbles.github.io/","paperUrl":"https://arxiv.org/abs/2406.18717","codeUrl":"https://github.com/coltonstearns/dynamic-gaussian-marbles","tags":[],"motion":["Tracking"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{stearns2024dynamic, title={Dynamic gaussian marbles for novel view synthesis of casual monocular videos}, author={Stearns, Colton and Harley, Adam and Uy, Mikaela and Dubost, Florian and Tombari, Federico and Wetzstein, Gordon and Guibas, Leonidas}, booktitle={SIGGRAPH Asia 2024 Conference Papers}, pages={1--11}, year={2024} }","title":"Dynamic gaussian marbles for novel view synthesis of casual monocular videos","authors":["Colton Stearns","Adam Harley","Mikaela Uy","Florian Dubost","Federico Tombari","Gordon Wetzstein","Leonidas Guibas"],"year":"2024","venue":"SIGGRAPH Asia","dataset":false,"survey":false,"bibkey":"stearns2024dynamic","prior":"Input","inputCondition":"Video","trainingStrategy":"Per-scene","filename":"gaussianmarble.json","thumbnailUrl":"images/gaussianmarble.webp"},{"title":"Generating Human Interaction Motions in Scenes with Text Control","authors":["Hongwei Yi","Justus Thies","Michael J. Black","Xue Bin Peng","Davis Rempe"],"year":"2024","venue":"ECCV","paperUrl":"https://arxiv.org/abs/2404.10685","projectPage":"https://research.nvidia.com/labs/toronto-ai/tesmo/","codeUrl":"https://github.com/nv-tlabs/tesmo","representation":["Template"],"motion":["Articulation"],"prior":"TD","inputCondition":"Text","trainingStrategy":"Feed-forward","interactionType":"HSI","task":"Human","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{tesmo,\n  title={Generating Human Interaction Motions in Scenes with Text Control},\n  author={Hongwei Yi and Justus Thies and Michael J. Black and Xue Bin Peng and Davis Rempe},\n  booktitle={ECCV},\n  year={2024}\n}","filename":"tesmo.json","thumbnailUrl":"images/tesmo.webp"},{"title":"Grid4D: 4D Decomposed Hash Encoding for High-Fidelity Dynamic Gaussian Splatting","authors":["Jiawei Xu","Zexin Fan","Jian Yang","Jin Xie"],"year":"2024","venue":"NeurIPS","paperUrl":"https://arxiv.org/abs/2410.20815","projectPage":"https://jiaweixu8.github.io/Grid4D-web/","codeUrl":"https://github.com/JiaweiXu8/Grid4D","representation":["Gaussian Splatting"],"motion":["Deformation","Space-Time"],"prior":"Input","inputCondition":"Video","trainingStrategy":"Per-scene","interactionType":"","task":"Scene","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{grid4d,\n  title={Grid4D: 4D Decomposed Hash Encoding for High-Fidelity Dynamic Gaussian Splatting},\n  author={Jiawei Xu and Zexin Fan and Jian Yang and Jin Xie},\n  booktitle={NeurIPS},\n  year={2024}\n}","filename":"grid4d.json","thumbnailUrl":"images/grid4d.webp"},{"title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","authors":["Han Liang","Wenqian Zhang","Wenxuan Li","Jingyi Yu","Lan Xu"],"year":"2024","venue":"IJCV","paperUrl":"https://arxiv.org/abs/2304.05684","projectPage":"https://tr3e.github.io/intergen-page/","codeUrl":"https://github.com/tr3e/InterGen","representation":["Template"],"motion":["Articulation"],"prior":"TD","inputCondition":"Text","trainingStrategy":"Feed-forward","interactionType":"HHI","task":"Human","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@article{liang2024intergen,\n  title={InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions},\n  author={Liang, Han and Zhang, Wenqian and Li, Wenxuan and Yu, Jingyi and Xu, Lan},\n  journal={IJCV},\n  year={2024}\n}","bibkey":"Intergen","filename":"intergen.json","thumbnailUrl":"images/intergen.webp"},{"representation":["Gaussian Splatting"],"task":"Object","category":"Video-to-4D","projectPage":"https://research.nvidia.com/labs/toronto-ai/l4gm/","paperUrl":"https://arxiv.org/abs/2406.10324","codeUrl":"https://github.com/nv-tlabs/L4GM-official","tags":[],"motion":["Per frame"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{ren2024l4gm,           title={L4GM: Large 4D Gaussian Reconstruction Model},           author={Ren, Jiawei and Xie, Kevin and Mirzaei, Ashkan and Liang, Hanxue and Zeng, Xiaohui and Kreis, Karsten and Liu, Ziwei and Torralba, Antonio and Fidler, Sanja and Kim, Seung Wook and Ling, Huan},           booktitle={Advances in Neural Information Processing Systems},           month={December},           year={2024} }","title":"L4GM: Large 4D Gaussian Reconstruction Model","authors":["Jiawei Ren","Kevin Xie","Ashkan Mirzaei","Hanxue Liang","Xiaohui Zeng","Karsten Kreis","Ziwei Liu","Antonio Torralba","Sanja Fidler","Seung Wook Kim","Huan Ling"],"year":"2024","venue":"NeurIPS","dataset":true,"survey":false,"bibkey":"ren2024l4gm","prior":"FM+TD","inputCondition":"Video","trainingStrategy":"Feed-forward","filename":"l4gm.json","thumbnailUrl":"images/l4gm.webp"},{"title":"MANUS: Markerless Grasp Capture using Articulated 3D Gaussians","authors":["Chandradeep Pokhariya","Ishaan Nikhil Shah","Angela Xing","Zekun Li","Kefan Chen","Avinash Sharma","Srinath Sridhar"],"year":"2024","venue":"CVPR","paperUrl":"https://arxiv.org/abs/2312.02137","projectPage":"https://ivl.cs.brown.edu/research/manus.html","codeUrl":"https://github.com/brown-ivl/manus","representation":["Template","Gaussian Splatting"],"motion":["Articulation"],"prior":"Input","inputCondition":"Multi-view","trainingStrategy":"Per-scene","interactionType":"Hand-O","task":"Hand","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{pokhariya2024manus,\n  title={MANUS: Markerless Grasp Capture using Articulated 3D Gaussians},\n  author={Pokhariya, Chandradeep and Shah, Ishaan Nikhil and Xing, Angela and Li, Zekun and Chen, Kefan and Sharma, Avinash and Sridhar, Srinath},\n  booktitle={CVPR},\n  year={2024}\n}","bibkey":"pokhariya2024manus","filename":"manus.json","thumbnailUrl":"images/manus.webp"},{"title":"NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis","authors":["Nilesh Kulkarni","Davis Rempe","Kyle Genova","Abhijit Kundu","Justin Johnson","David Fouhey","Leonidas Guibas"],"year":"2024","venue":"CVPR","paperUrl":"https://arxiv.org/abs/2307.07511","projectPage":"https://nileshkulkarni.github.io/nifty/","codeUrl":"","representation":["Template"],"motion":["Articulation"],"prior":"TD","inputCondition":"Object","trainingStrategy":"Feed-forward","interactionType":"HOI","task":"Human","category":[],"tags":[],"interaction":"","codeAvailability":false,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{kulkarni2024nifty,\n  title={NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis},\n  author={Kulkarni, Nilesh and Rempe, Davis and Genova, Kyle and Kundu, Abhijit and Johnson, Justin and Fouhey, David and Guibas, Leonidas},\n  booktitle={CVPR},\n  year={2024}\n}","bibkey":"kulkarni2024nifty","filename":"nifty.json","thumbnailUrl":"images/nifty.webp"},{"representation":["Point Cloud"],"task":"Scene","category":"Image-to-4D","projectPage":"https://niopeng.github.io/PAPR-in-Motion/","paperUrl":"https://arxiv.org/abs/2406.05533","codeUrl":"https://github.com/niopeng/PAPR-in-Motion","tags":[],"motion":["Tracking"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{peng2024papr,       title={PAPR in Motion: Seamless Point-level 3D Scene Interpolation},       author={Shichong Peng and Yanshu Zhang and Ke Li},       booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},       year={2024}   }","title":"PAPR in Motion: Seamless Point-level 3D Scene Interpolation","authors":["Shichong Peng","Yanshu Zhang","Ke Li"],"year":"2024","venue":"CVPR","dataset":false,"survey":false,"bibkey":"peng2024papr","prior":"Input","inputCondition":"Image","trainingStrategy":"Per-scene","filename":"paprinmotion.json","thumbnailUrl":"images/paprinmotion.webp"},{"representation":["Template","Mesh"],"task":"Human","category":["Video-to-4D","3D-to-4D"],"projectPage":"https://qingqing-zhao.github.io/PhysAvatar","paperUrl":"https://arxiv.org/abs/2404.04421","codeUrl":"https://github.com/y-zheng18/PhysAvatar","tags":[],"motion":["Articulation","Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{zheng2024physavatar,   title={Physavatar: Learning the physics of dressed 3d avatars from visual observations},   author={Zheng, Yang and Zhao, Qingqing and Yang, Guandao and Yifan, Wang and Xiang, Donglai and Dubost, Florian and Lagun, Dmitry and Beeler, Thabo and Tombari, Federico and Guibas, Leonidas and others},   booktitle={European Conference on Computer Vision},   pages={262--284},   year={2024},   organization={Springer} }","title":"Physavatar: Learning the physics of dressed 3d avatars from visual observations","authors":["Yang Zheng","Qingqing Zhao","Guandao Yang","Wang Yifan","Donglai Xiang","Florian Dubost","Dmitry Lagun","Thabo Beeler","Federico Tombari","Leonidas Guibas","others"],"year":"2024","venue":"ECCV","dataset":false,"survey":false,"bibkey":"PhysAavatar24","prior":"Input","inputCondition":"Video+Mesh","trainingStrategy":"Per-scene","filename":"physavatar.json","thumbnailUrl":"images/physavatar.webp"},{"title":"Real2Code: Reconstruct Articulated Objects via Code Generation","authors":["Zhao Mandi","Yijia Weng","Dominik Bauer","Shuran Song"],"year":"2024","venue":"ICLR","paperUrl":"https://arxiv.org/abs/2406.08474","projectPage":"https://real2code.github.io/","codeUrl":"https://github.com/MandiZhao/real2code","representation":["Part","Mesh"],"motion":["Articulation"],"prior":"TD+LLM","inputCondition":"Multi-view","trainingStrategy":"Feed-forward","interactionType":"","task":"Object","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{real2code,\n  title={Real2Code: Reconstruct Articulated Objects via Code Generation},\n  author={Zhao Mandi and Yijia Weng and Dominik Bauer and Shuran Song},\n  booktitle={ICLR},\n  year={2024}\n}","filename":"real2code.json","thumbnailUrl":"images/real2code.webp"},{"representation":["Gaussian Splatting"],"task":"Object","category":["Video-to-4D"],"projectPage":"https://sc4d.github.io/","paperUrl":"https://arxiv.org/abs/2404.03736","codeUrl":"https://github.com/JarrentWu1031/SC4D","tags":[],"motion":["Articulation","Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{wu2024sc4d,   title={Sc4d: Sparse-controlled video-to-4d generation and motion transfer},   author={Wu, Zijie and Yu, Chaohui and Jiang, Yanqin and Cao, Chenjie and Wang, Fan and Bai, Xiang},   booktitle={European Conference on Computer Vision},   pages={361--379},   year={2024},   organization={Springer} }","title":"Sc4d: Sparse-controlled video-to-4d generation and motion transfer","authors":["Zijie Wu","Chaohui Yu","Yanqin Jiang","Chenjie Cao","Fan Wang","Xiang Bai"],"year":"2024","venue":"ECCV","dataset":false,"survey":false,"bibkey":"wu_sc4d_2024","prior":"FM","inputCondition":"Video","trainingStrategy":"Per-scene","filename":"sc4d.json","thumbnailUrl":"images/sc4d.webp"},{"title":"Shape of Motion: 4D Reconstruction from a Single Video","authors":["Qianqian Wang","Vickie Ye","Hang Gao","Jake Austin","Zhengqi Li","Angjoo Kanazawa"],"year":"2024","venue":"ArXiv","paperUrl":"https://arxiv.org/abs/2407.13764","projectPage":"https://shape-of-motion.github.io/","codeUrl":"https://github.com/vye16/shape-of-motion","representation":["Gaussian Splatting"],"motion":["Deformation","Tracking"],"prior":"Input","inputCondition":"Video","trainingStrategy":"Per-scene","interactionType":"","task":"Scene","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@article{shapeofmotion,\n  title={Shape of Motion: 4D Reconstruction from a Single Video},\n  author={Qianqian Wang and Vickie Ye and Hang Gao and Jake Austin and Zhengqi Li and Angjoo Kanazawa},\n  journal={arXiv preprint arXiv:2407.13764},\n  year={2024}\n}","filename":"shapeofmotion.json","thumbnailUrl":"images/shapeofmotion.webp"},{"representation":["Gaussian Splatting"],"task":"Object","category":["Text-to-4D","Video-to-4D"],"projectPage":"https://nju-3dv.github.io/projects/STAG4D/","paperUrl":"https://arxiv.org/abs/2403.14939","codeUrl":"https://github.com/zeng-yifei/STAG4D","tags":[],"bibtex":"@inproceedings{zeng2024stag4d,   title={Stag4d: Spatial-temporal anchored generative 4d gaussians},   author={Zeng, Yifei and Jiang, Yanqin and Zhu, Siyu and Lu, Yuanxun and Lin, Youtian and Zhu, Hao and Hu, Weiming and Cao, Xun and Yao, Yao},   booktitle={European Conference on Computer Vision},   pages={163--179},   year={2024},   organization={Springer} }","motion":["Deformation"],"codeAvailability":true,"interaction":"","title":"STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians","authors":["Yifei Zeng","Yanqin Jiang","Siyu Zhu","Yuanxun Lu","Youtian Lin","Hao Zhu","Weiming Hu","Xun Cao","Yao Yao"],"year":"2024","venue":"ECCV","dataset":false,"survey":false,"bibkey":"zeng2024stag4d","prior":"FM","inputCondition":"Text/Video","trainingStrategy":"Per-scene","filename":"stag4d.json","thumbnailUrl":"images/stag4d.webp"},{"representation":"Gaussian Splatting","task":"Scene","category":"Video-to-4D","projectPage":"https://dnvtmf.github.io/SP_GS.github.io/","paperUrl":"https://arxiv.org/abs/2406.03697","codeUrl":"https://github.com/dnvtmf/SP_GS","tags":[],"motion":"Deformation","codeAvailability":true,"interaction":"","bibtex":"@inproceedings{ icml2024-sp-gs, title={Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstruction}, author={Diwen Wan, Ruijie Lu, Gang Zeng}, booktitle={Forty-first International Conference on Machine Learning}, year={2024} }","title":"Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstruction","authors":["Ruijie Lu, Gang Zeng Diwen Wan"],"year":"2024","venue":"ICML","dataset":false,"survey":false,"filename":"spgs.json","thumbnailUrl":"images/spgs.webp"},{"representation":["Template"],"task":"Human","category":["Text-to-4D"],"projectPage":"https://tada.is.tue.mpg.de/","paperUrl":"https://arxiv.org/abs/2308.10899","codeUrl":"https://github.com/TingtingLiao/TADA?tab=readme-ov-file","tags":[],"motion":["Articulation","Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{liao2024tada, title={TADA! Text to Animatable Digital Avatars}, author={Liao, Tingting and Yi, Hongwei and Xiu, Yuliang and Tang, Jiaxiang and Huang, Yangyi and Thies, Justus and Black, Michael J.}, booktitle={International Conference on 3D Vision (3DV)}, year={2024} }","title":"TADA! Text to Animatable Digital Avatars","authors":["Tingting Liao","Hongwei Yi","Yuliang Xiu","Jiaxiang Tang","Yangyi Huang","Justus Thies","Michael J. Black"],"year":"2024","venue":"3DV","dataset":false,"survey":false,"bibkey":"liao2024tada","prior":"FM+LLM","inputCondition":"Text","trainingStrategy":"Per-scene","filename":"tada.json","thumbnailUrl":"images/tada.webp"},{"representation":"NeRF","task":"Scene","category":["Text-to-4D"],"projectPage":"https://sherwinbahmani.github.io/tc4d/","paperUrl":"https://arxiv.org/pdf/2403.17920","codeUrl":"https://github.com/sherwinbahmani/tc4d","tags":[],"motion":"Deformation","codeAvailability":true,"interaction":"","bibtex":"@inproceedings{bahmani2024tc4d, title={Tc4d: Trajectory-conditioned text-to-4d generation}, author={Bahmani, Sherwin and Liu, Xian and Yifan, Wang and Skorokhodov, Ivan and Rong, Victor and Liu, Ziwei and Liu, Xihui and Park, Jeong Joon and Tulyakov, Sergey and Wetzstein, Gordon and others}, booktitle={European Conference on Computer Vision},pages={53--72},year={2024},organization={Springer}}","title":"TC4d: Trajectory-conditioned text-to-4d generation","authors":["Sherwin Bahmani","Xian Liu","Wang Yifan","Ivan Skorokhodov","Victor Rong","Ziwei Liu","Xihui Liu","Jeong Joon Park","Sergey Tulyakov","Gordon Wetzstein","others"],"year":"2024","venue":"ECCV","dataset":false,"survey":false,"filename":"TC4D.json","thumbnailUrl":"images/TC4D.webp"},{"title":"Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis","authors":["Bohan Zeng","Ling Yang","Siyu Li","Jiaming Liu","Zixiang Zhang","Juanxi Tian","Kaixin Zhu","Yongzhen Guo","Fu-Yun Wang","Minkai Xu","Stefano Ermon","Wentao Zhang"],"year":"2024","venue":"ICLR","paperUrl":"https://arxiv.org/abs/2410.07155","projectPage":"","codeUrl":"https://github.com/YangLing0818/Trans4D","representation":["Gaussian Splatting"],"motion":["Deformation"],"prior":"FM+LLM","inputCondition":"Text","trainingStrategy":"Per-scene","interactionType":"","task":"Scene","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{trans4d,\n  title={Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis},\n  author={Bohan Zeng and Ling Yang and Siyu Li and Jiaming Liu and Zixiang Zhang and Juanxi Tian and Kaixin Zhu and Yongzhen Guo and Fu-Yun Wang and Minkai Xu and Stefano Ermon and Wentao Zhang},\n  booktitle={ICLR},\n  year={2024}\n}","filename":"trans4d.json","thumbnailUrl":"images/trans4d.webp"},{"representation":"Gaussian Splatting","task":"Object","category":"Text-to-4D","projectPage":"https://vidu4d-dgs.github.io/","paperUrl":"https://arxiv.org/abs/2405.16822","codeUrl":"https://github.com/yikaiw/vidu4d","tags":[],"motion":"Deformation","codeAvailability":true,"interaction":"","bibtex":"@inproceedings{wang2024vidu4d,   title={Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels},   author={Yikai Wang and Xinzhou Wang and Zilong Chen and Zhengyi Wang and Fuchun Sun and Jun Zhu},   booktitle={Advances in Neural Information Processing Systems (NeurIPS)},   year={2024} }","title":"Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels","authors":["Yikai Wang","Xinzhou Wang","Zilong Chen","Zhengyi Wang","Fuchun Sun","Jun Zhu"],"year":"2024","venue":"NeurIPS","dataset":false,"survey":false,"filename":"vidu4d.json","thumbnailUrl":"images/vidu4d.webp"},{"representation":"","task":"Object","category":"","projectPage":"https://hi-zhengcheng.github.io/vividzoo/","paperUrl":"https://arxiv.org/pdf/2406.08659v1","codeUrl":"https://github.com/hi-zhengcheng/vividzoo","tags":[],"motion":"","codeAvailability":true,"interaction":"","bibtex":"@misc{li2024vividzoo,  title={Vivid-ZOO: Multi-View Video Generation with Diffusion Model},   author={Bing Li and Cheng Zheng and Wenxuan Zhu and Jinjie Mai and Biao Zhang and Peter Wonka and Bernard Ghanem},  year={2024},  eprint={2406.08659},  archivePrefix={arXiv},}","title":"Vivid-ZOO: Multi-View Video Generation with Diffusion Model","authors":["Bing Li","Cheng Zheng","Wenxuan Zhu","Jinjie Mai","Biao Zhang","Peter Wonka","Bernard Ghanem"],"year":"2024","venue":"NeurIPS","dataset":true,"survey":false,"filename":"vividzoo.json","thumbnailUrl":"images/vividzoo.webp"},{"representation":["Graph"],"task":"Scene","category":"4D understanding","projectPage":"","paperUrl":"https://arxiv.org/abs/2405.10305","codeUrl":"https://github.com/Jingkang50/PSG4D","tags":[],"motion":["Scene Graph"],"codeAvailability":true,"interaction":"Human-Object Interaction","bibtex":"@inproceedings{yang2023psg4d,     author = {Yang, Jingkang and Cen, Jun and Peng, Wenxuan and Liu, Shuai and Hong, Fangzhou and Li, Xiangtai and Zhou, Kaiyang and Chen, Qifeng and Liu, Ziwei}     title = {4D Panoptic Scene Graph Generation},     booktitle = {NeurIPS},     year = {2023}, }","title":"4D Panoptic Scene Graph Generation","authors":["Jingkang Yang","Jun Cen","Wenxuan Peng","Shuai Liu","Fangzhou Hong","Xiangtai Li","Kaiyang Zhou","Qifeng Chen","Ziwei Liu"],"year":"2023","venue":"NeurIPS","dataset":true,"survey":false,"bibkey":"4DPanoSceneGraph","prior":"TD","inputCondition":"Point Cloud","trainingStrategy":"Feed-forward","filename":"4dpsg.json","thumbnailUrl":"images/4dpsg.webp"},{"representation":["Gaussian Splatting"],"task":"Object","category":"Video-to-4D","projectPage":"https://vita-group.github.io/4DGen/","paperUrl":"https://arxiv.org/abs/2312.17225","codeUrl":"https://github.com/VITA-Group/4DGen","tags":[],"motion":["Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@article{yin20234dgen,   title={4dgen: Grounded 4d content generation with spatial-temporal consistency},   author={Yin, Yuyang and Xu, Dejia and Wang, Zhangyang and Zhao, Yao and Wei, Yunchao},   journal={arXiv preprint arXiv:2312.17225},   year={2023} }}","title":"4dgen: Grounded 4d content generation with spatial-temporal consistency","authors":["Yuyang Yin","Dejia Xu","Zhangyang Wang","Yao Zhao","Yunchao Wei"],"year":"2023","venue":"ArXiv","dataset":false,"survey":false,"bibkey":"yin_4dgen_2023","prior":"FM","inputCondition":"Video","trainingStrategy":"Per-scene","filename":"4dgen.json","thumbnailUrl":"images/4dgen.webp"},{"representation":["Gaussian Splatting"],"task":"Object","category":["Image-to-4D"],"projectPage":"https://jiawei-ren.github.io/projects/dreamgaussian4d/","paperUrl":"https://arxiv.org/pdf/2312.17142","codeUrl":"https://github.com/jiawei-ren/dreamgaussian4d","tags":[],"motion":["Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@article{ren2023dreamgaussian4d,title={DreamGaussian4D: Generative 4D Gaussian Splatting},author={Ren, Jiawei and Pan, Liang and Tang, Jiaxiang and Zhang, Chi and Cao, Ang and Zeng, Gang and Liu, Ziwei},journal={ArXiv},year={2023}}","title":"DreamGaussian4D: Generative 4D Gaussian Splatting","authors":["Jiawei Ren","Liang Pan","Jiaxiang Tang","Chi Zhang","Ang Cao","Gang Zeng","Ziwei Liu"],"year":"2023","venue":"ArXiv","dataset":false,"survey":false,"bibkey":"ren2023dreamgaussian4d","prior":"FM","inputCondition":"Image","trainingStrategy":"Per-scene","filename":"dg4d.json","thumbnailUrl":"images/dg4d.webp"},{"representation":"NeRF","task":"Scene","category":["Video-to-4D"],"projectPage":"https://mightychaos.github.io/projects/fsdnerf/","paperUrl":"https://arxiv.org/pdf/2303.16333.pdf","codeUrl":"","tags":[],"motion":["Tracking","Deformation"],"codeAvailability":false,"interaction":"","bibtex":"@InProceedings{Wang_2023_CVPR, author = {Wang, Chaoyang and MacDonald, Lachlan Ewen and Jeni, Laszlo A. and Lucey, Simon}, title = {Flow Supervision for Deformable NeRF}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21128-21137} }","title":"Flow Supervision for Deformable NeRF","authors":["Chaoyang Wang","Lachlan Ewen MacDonald","Laszlo A. Jeni","Simon Lucey"],"year":"2023","venue":"CVPR","dataset":false,"survey":false,"filename":"fsdnerf.json","thumbnailUrl":"images/fsdnerf.webp"},{"title":"HandNeRF: Neural Radiance Fields for Animatable Interacting Hands","authors":["Zhiyang Guo","Wengang Zhou","Min Wang","Li Li","Houqiang Li"],"year":"2023","venue":"CVPR","paperUrl":"https://arxiv.org/abs/2303.13825","projectPage":"","codeUrl":"","representation":["Template","NeRF"],"motion":["Articulation","Deformation"],"prior":"Input","inputCondition":"Multi-view","trainingStrategy":"Per-scene","interactionType":"Hand-Hand","task":"Hand","category":[],"tags":[],"interaction":"","codeAvailability":false,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{guo2023handnerf,\n  title={HandNeRF: Neural Radiance Fields for Animatable Interacting Hands},\n  author={Guo, Zhiyang and Zhou, Wengang and Wang, Min and Li, Li and Li, Houqiang},\n  booktitle={CVPR},\n  year={2023}\n}","bibkey":"guo2023handnerf","filename":"handnerf.json","thumbnailUrl":"images/handnerf.webp"},{"title":"HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video","authors":["Jia-Wei Liu","Yan-Pei Cao","Tianyuan Yang","Eric Zhongcong Xu","Jussi Keppo","Ying Shan","Xiaohu Qie","Mike Zheng Shou"],"year":"2023","venue":"ICCV","paperUrl":"https://arxiv.org/abs/2304.12281","projectPage":"https://showlab.github.io/HOSNeRF/","codeUrl":"https://github.com/TencentARC/HOSNeRF","representation":["Template","NeRF"],"motion":["Articulation","Deformation"],"prior":"Input","inputCondition":"Video","trainingStrategy":"Per-scene","interactionType":"HOI/HSI","task":"Human","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{liu2023hosnerf,\n  title={HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video},\n  author={Liu, Jia-Wei and Cao, Yan-Pei and Yang, Tianyuan and Xu, Eric Zhongcong and Keppo, Jussi and Shan, Ying and Qie, Xiaohu and Shou, Mike Zheng},\n  booktitle={ICCV},\n  year={2023}\n}","bibkey":"liu2023hosnerf","filename":"hosnerf.json","thumbnailUrl":"images/hosnerf.webp"},{"title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","authors":["Sirui Xu","Zhengyuan Li","Yu-Xiong Wang","Liang-Yan Gui"],"year":"2023","venue":"ICCV","paperUrl":"https://arxiv.org/abs/2308.16905","projectPage":"https://sirui-xu.github.io/InterDiff/","codeUrl":"https://github.com/Sirui-Xu/InterDiff","representation":["Template","Mesh"],"motion":["Articulation"],"prior":"TD","inputCondition":"Motion","trainingStrategy":"Feed-forward","interactionType":"HOI","task":"Human","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{xu2023interdiff,\n  title={InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion},\n  author={Xu, Sirui and Li, Zhengyuan and Wang, Yu-Xiong and Gui, Liang-Yan},\n  booktitle={ICCV},\n  year={2023}\n}","bibkey":"xu2023interdiff","filename":"interdiff.json","thumbnailUrl":"images/interdiff.webp"},{"representation":["Point Cloud"],"task":"Object","category":"3D-to-4D","projectPage":"https://dyfcalid.github.io/NeuralPCI","paperUrl":"https://arxiv.org/abs/2303.15126","codeUrl":"https://github.com/ispc-lab/NeuralPCI","tags":[],"motion":["Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{zheng2023neuralpci,     title     = {NeuralPCI: Spatio-temporal Neural Field for 3D Point Cloud Multi-frame Non-linear Interpolation},     author    = {Zheng, Zehan and Wu, Danni and Lu, Ruisi and Lu, Fan and Chen, Guang and Jiang, Changjun},     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},     year      = {2023}     }","title":"NeuralPCI: Spatio-temporal Neural Field for 3D Point Cloud Multi-frame Non-linear Interpolation","authors":["Zehan Zheng","Danni Wu","Ruisi Lu","Fan Lu","Guang Chen","Changjun Jiang"],"year":"2023","venue":"CVPR","dataset":false,"survey":false,"bibkey":"zheng2023neuralpci","prior":"Input","inputCondition":"Point Cloud","trainingStrategy":"Per-scene","filename":"neuralpci.json","thumbnailUrl":"images/neuralpci.webp"},{"representation":["Part","NeRF"],"task":"Object","category":["Image-to-4D"],"projectPage":"https://3dlg-hcvc.github.io/paris/","paperUrl":"https://arxiv.org/abs/2308.07391","codeUrl":"https://github.com/3dlg-hcvc/paris","tags":[],"motion":["Articulation"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{jiayi2023paris, author = {Liu, Jiayi and Mahdavi-Amiri, Ali and Savva, Manolis}, title = {{PARIS}: Part-level Reconstruction and Motion Analysis for Articulated Objects}, year = {2023}, booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)} }","title":"PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects","authors":["Jiayi Liu","Ali Mahdavi-Amiri","Manolis Savva"],"year":"2023","venue":"ICCV","dataset":false,"survey":false,"bibkey":"liu2023paris","prior":"Input","inputCondition":"Image","trainingStrategy":"Per-scene","filename":"paris.json","thumbnailUrl":"images/paris.webp"},{"representation":["NeRF"],"task":"Scene","category":"Video-to-4D","projectPage":"https://sungheonpark.github.io/tempinterpnerf/","paperUrl":"https://arxiv.org/abs/2302.09311","codeUrl":"","tags":[],"motion":["Space-Time"],"codeAvailability":false,"interaction":"","bibtex":"@inproceedings{park2023temporal,   title={Temporal interpolation is all you need for dynamic neural radiance fields},   author={Park, Sungheon and Son, Minjung and Jang, Seokhwan and Ahn, Young Chun and Kim, Ji-Yeon and Kang, Nahyup},   booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},   pages={4212--4221},   year={2023} }","title":"Temporal interpolation is all you need for dynamic neural radiance fields","authors":["Sungheon Park","Minjung Son","Seokhwan Jang","Young Chun Ahn","Ji-Yeon Kim","Nahyup Kang"],"year":"2023","venue":"CVPR","dataset":false,"survey":false,"bibkey":"park2023temporal","prior":"Input","inputCondition":"Video","trainingStrategy":"Per-scene","filename":"tempint.json","thumbnailUrl":"images/tempint.webp"},{"representation":["NeRF"],"task":["Object","Scene"],"category":["Text-to-4D"],"projectPage":"https://make-a-video3d.github.io/","paperUrl":"https://arxiv.org/abs/2301.11280","codeUrl":"","tags":[],"motion":["Deformation"],"codeAvailability":false,"interaction":"","bibtex":"@article{singer2023text,  title={Text-to-4d dynamic scene generation},  author={Singer, Uriel and Sheynin, Shelly and Polyak, Adam and Ashual, Oron and Makarov, Iurii and Kokkinos, Filippos and Goyal, Naman and Vedaldi, Andrea and Parikh, Devi and Johnson, Justin and others},  journal={ICML},  year={2023}}","title":"Text-to-4d dynamic scene generation","authors":["Uriel Singer","Shelly Sheynin","Adam Polyak","Oron Ashual","Iurii Makarov","Filippos Kokkinos","Naman Goyal","Andrea Vedaldi","Devi Parikh","Justin Johnson","others"],"year":"2023","venue":"ICML","dataset":false,"survey":false,"bibkey":"singer2023text","prior":"FM","inputCondition":"Text","trainingStrategy":"Per-scene","filename":"mav3d.json","thumbnailUrl":"images/mav3d.webp"},{"representation":["NeRF"],"task":"Object","category":"Video-to-4D","projectPage":"","paperUrl":"https://arxiv.org/abs/2205.14332","codeUrl":"https://github.com/GANWANSHUI/V4D","tags":[],"motion":["Space-Time"],"codeAvailability":true,"interaction":"","bibtex":"@article{gan2023v4d,   title={V4d: Voxel for 4d novel view synthesis},   author={Gan, Wanshui and Xu, Hongbin and Huang, Yi and Chen, Shifeng and Yokoya, Naoto},   journal={IEEE Transactions on Visualization and Computer Graphics},   year={2023},   publisher={IEEE} }","title":"V4d: Voxel for 4d novel view synthesis","authors":["Wanshui Gan","Hongbin Xu","Yi Huang","Shifeng Chen","Naoto Yokoya"],"year":"2023","venue":"IEEE TVCG","dataset":false,"survey":false,"bibkey":"gan2023v4d","prior":"Input","inputCondition":"Video","trainingStrategy":"Per-scene","filename":"v4d.json","thumbnailUrl":"images/v4d.webp"},{"representation":["Template","NeRF"],"task":"Human","category":"Video-to-4D","projectPage":"https://moygcc.github.io/vid2avatar/","paperUrl":"https://arxiv.org/abs/2302.11566","codeUrl":"https://github.com/MoyGcc/vid2avatar","tags":[],"motion":["Articulation","Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@inproceedings{guo2023vid2avatar,       title={Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition},       author={Guo, Chen and Jiang, Tianjian and Chen, Xu and Song, Jie and Hilliges, Otmar},           booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},       month     = {June},       year      = {2023},     }","title":"Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition","authors":["Chen Guo","Tianjian Jiang","Xu Chen","Jie Song","Otmar Hilliges"],"year":"2023","venue":"CVPR","dataset":false,"survey":false,"bibkey":"guo2023vid2avatar","prior":"Input","inputCondition":"Video","trainingStrategy":"Per-scene","filename":"vid2avatar.json","thumbnailUrl":"images/vid2avatar.webp"},{"title":"Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation","authors":["Anthony Simeonov","Yilun Du","Andrea Tagliasacchi","Joshua B. Tenenbaum","Alberto Rodriguez","Pulkit Agrawal","Vincent Sitzmann"],"year":"2022","venue":"ICRA","paperUrl":"https://arxiv.org/abs/2112.05124","projectPage":"https://yilundu.github.io/ndf/","codeUrl":"https://github.com/anthonysimeonov/ndf_robot","representation":["Point Cloud"],"motion":[],"prior":"TD","inputCondition":"Point Cloud","trainingStrategy":"Feed-forward","interactionType":"OOI","task":"Object","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{simeonov2022neural,\n  title={Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation},\n  author={Simeonov, Anthony and Du, Yilun and Tagliasacchi, Andrea and Tenenbaum, Joshua B. and Rodriguez, Alberto and Agrawal, Pulkit and Sitzmann, Vincent},\n  booktitle={ICRA},\n  year={2022}\n}","bibkey":"NeuralDescriptorFields","filename":"ndf.json","thumbnailUrl":"images/ndf.webp"},{"title":"3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding","authors":["Shengheng Deng","Xun Xu","Chaozheng Wu","Ke Chen","Kui Jia"],"year":"2021","venue":"CVPR","paperUrl":"https://arxiv.org/abs/2103.16397","projectPage":"","codeUrl":"https://github.com/Gorilla-Lab-SCUT/AffordanceNet","representation":["Point Cloud"],"motion":[],"prior":"TD","inputCondition":"Point Cloud","trainingStrategy":"Feed-forward","interactionType":"Affordance prediction","task":"Object","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{deng20213d,\n  title={3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding},\n  author={Deng, Shengheng and Xu, Xun and Wu, Chaozheng and Chen, Ke and Jia, Kui},\n  booktitle={CVPR},\n  year={2021}\n}","bibkey":"3DAffordanceNet","filename":"3daffordancenet.json","thumbnailUrl":"images/3daffordancenet.webp"},{"representation":["Graph"],"task":"Scene","category":"","projectPage":"https://homeactiongenome.org/","paperUrl":"https://arxiv.org/pdf/2105.05226","codeUrl":"https://github.com/nishantrai18/homage","tags":[],"motion":"","codeAvailability":true,"interaction":"Human-Scene Interaction","bibtex":"@inproceedings{rai2021home,   title={Home action genome: Cooperative compositional action understanding},   author={Rai, Nishant and Chen, Haofeng and Ji, Jingwei and Desai, Rishi and Kozuka, Kazuki and Ishizaka, Shun and Adeli, Ehsan and Niebles, Juan Carlos},   booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},   pages={11184--11193},   year={2021} }","title":"Home action genome: Cooperative compositional action understanding","authors":["Nishant Rai","Haofeng Chen","Jingwei Ji","Rishi Desai","Kazuki Kozuka","Shun Ishizaka","Ehsan Adeli","Juan Carlos Niebles"],"year":"2021","venue":"CVPR","dataset":true,"survey":false,"filename":"homage.json","thumbnailUrl":"images/homage.webp"},{"title":"Populating 3D Scenes by Learning Human-Scene Interaction","authors":["Mohamed Hassan","Partha Ghosh","Joachim Tesch","Dimitrios Tzionas","Michael J. Black"],"year":"2021","venue":"CVPR","paperUrl":"https://arxiv.org/abs/2012.11581","projectPage":"https://posa.is.tue.mpg.de/","codeUrl":"https://github.com/mohamedhassanmus/POSA","representation":["Template"],"motion":[],"prior":"TD","inputCondition":"Mesh+Scene","trainingStrategy":"Feed-forward","interactionType":"HSI","task":"Human","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{hassan2021populating,\n  title={Populating 3D Scenes by Learning Human-Scene Interaction},\n  author={Hassan, Mohamed and Ghosh, Partha and Tesch, Joachim and Tzionas, Dimitrios and Black, Michael J.},\n  booktitle={CVPR},\n  year={2021}\n}","bibkey":"POSA","filename":"posa.json","thumbnailUrl":"images/posa.webp"},{"representation":["Graph"],"task":"Scene","category":"Video-to-4D","projectPage":"https://www.youtube.com/watch?v=SWbofjhyPzI","paperUrl":"https://arxiv.org/abs/2002.06289","codeUrl":"https://github.com/MIT-SPARK/Kimera","tags":[],"motion":["Scene Graph"],"codeAvailability":true,"interaction":"","bibtex":"@InProceedings{Rosinol20rss-dynamicSceneGraphs,   title = {3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans},   author = {A. Rosinol and A. Gupta and M. Abate and J. Shi and L. Carlone},   year = {2020},   booktitle = {Robotics: Science and Systems (RSS)},   pdf = {https://arxiv.org/pdf/2002.06289.pdf} }","title":"3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans","authors":["A. Rosinol","A. Gupta","M. Abate","J. Shi","L. Carlone"],"year":"2020","venue":"RSS","bibkey":"3DDSG","prior":"Input","inputCondition":"Stereo+IMU","trainingStrategy":"Per-scene","filename":"3dsg.json","thumbnailUrl":"images/3dsg.webp"},{"title":"GanHand: Predicting Human Grasp Affordances in Multi-Object Scenes","authors":["Enric Corona","Albert Pumarola","Guillem Alenyà","Francesc Moreno-Noguer","Grégory Rogez"],"year":"2020","venue":"CVPR","paperUrl":"https://openaccess.thecvf.com/content_CVPR_2020/html/Corona_GanHand_Predicting_Human_Grasp_Affordances_in_Multi-Object_Scenes_CVPR_2020_paper.html","projectPage":"https://enriccorona.github.io/ganhand/","codeUrl":"https://github.com/enriccorona/GanHand","representation":["Template"],"motion":[],"prior":"TD","inputCondition":"Image","trainingStrategy":"Feed-forward","interactionType":"Hand-O","task":"Hand","category":[],"tags":[],"interaction":"","codeAvailability":true,"dataset":false,"survey":false,"doi":"","bibtex":"@inproceedings{corona2020ganhand,\n  title={GanHand: Predicting Human Grasp Affordances in Multi-Object Scenes},\n  author={Corona, Enric and Pumarola, Albert and Aleny{\\`a}, Guillem and Moreno-Noguer, Francesc and Rogez, Gr{\\'e}gory},\n  booktitle={CVPR},\n  year={2020}\n}","bibkey":"corona2020ganhand","filename":"ganhand.json","thumbnailUrl":"images/ganhand.webp"},{"representation":["Point Cloud"],"task":"Object","category":"3D-to-4D","projectPage":"https://vcc.tech/research/2019/RPMNet","paperUrl":"https://arxiv.org/abs/2006.14865","codeUrl":"https://github.com/Salingo/RPM-Net","tags":[],"motion":["Deformation"],"codeAvailability":true,"interaction":"","bibtex":"@article{RPMNet19, title = {RPM-Net: Recurrent Prediction of Motion and Parts from Point Cloud}, author = {Zihao Yan and Ruizhen Hu and Xingguang Yan and Luanmin Chen and Oliver van Kaick and Hao Zhang and Hui Huang}, journal = {ACM Transactions on Graphics (Proceedings of SIGGRAPH ASIA 2019)}, volume = {38}, number = {6}, pages = {240:1--240:15},   year = {2019}, } ","title":"RPM-Net: Recurrent Prediction of Motion and Parts from Point Cloud","authors":["Zihao Yan","Ruizhen Hu","Xingguang Yan","Luanmin Chen","Oliver van Kaick","Hao Zhang","Hui Huang"],"year":"2019","venue":"SIGGRAPH Asia","dataset":true,"survey":false,"bibkey":"yan2020rpm","prior":"TD","inputCondition":"Point Cloud","trainingStrategy":"Feed-forward","filename":"rpmnet.json","thumbnailUrl":"images/rpmnet.webp"}]}