Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera
Zhengdi Yu, Stefanos Zafeiriou, Tolga Birdal
2025Year
8Top-tier citations
Abstract
Input video Dyn-HaMR (Ours) HaMeR Camera motion Hand motion Figure 1. Dyn-HaMR as a remedy for the motion entanglement in the wild. The green and red arrows represent the direction of the hand motion. Dyn-HaMR (Ours) can disentangle the camera and object poses to recover the 4D global hand motion in the real world whilst state-of-the-art 3D hand reconstruction methods like HaMeR [37], IntagHand [25] and ACR [51] fail to do so since they cannot disentangle the sources of motion.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers8
- Vision-Language-Action Pretraining from Large-Scale Human VideosHao Luo, Yicheng Feng, Wanpeng Zhang, Sipeng Zheng et al.ICML 2026 · 104 citations
- Geometric Neural Distance Fields for Learning Human Motion PriorsZhengdi Yu, Simone Foti, Linguang Zhang, Amy Zhao et al.CVPR 2026 · 8 citations
- MagicHOI: Leveraging 3D Priors for Accurate Hand-Object Reconstruction from Short Monocular Video ClipsShibo Wang, Haonan He, Maria Parelli, Christoph Gebhardt et al.ICCV 2025 · 2 citations
- HandX: Scaling Bimanual Motion and Interaction GenerationZimu Zhang, Yucheng Zhang, Xiyan Xu, Ziyin Wang et al.CVPR 2026 · 2 citations
- UniHand: A Unified Model for Diverse Controlled 4D Hand Motion ModelingZhihao Sun, Tong Wu, Ruirui Tu, Daoguo Dong et al.ICLR 2026 · 2 citations
Builds on28
- DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D CamerasZachary Teed, Jia DengNeurIPS 2021 · 1,248 citations
- ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationYufei Xu, Jing Zhang, Qiming Zhang, Dacheng TaoNeurIPS 2022 · 1,105 citations
- HuMoR: 3D Human Motion Model for Robust Pose EstimationDavis Rempe, Tolga Birdal, Aaron Hertzmann, Jimei Yang et al.ICCV 2021 · 398 citations
- Deep Patch Visual OdometryZachary Teed, Lahav Lipson, Jia DengNeurIPS 2023 · 323 citations
- H2O: Two Hands Manipulating Objects for First Person Interaction RecognitionTaein Kwon, Bugra Tekin, Jan Stühmer, Federica Bogo et al.ICCV 2021 · 271 citations
Related papers
- Decoupling Human and Camera Motion from Videos in the WildVickie Ye, Georgios Pavlakos, Jitendra Malik, Angjoo KanazawaCVPR 2023
- HaWoR: World-Space Hand Motion Reconstruction from Egocentric VideosJinglei Zhang, Jiankang Deng, Chao Ma, Rolandos Alexandros PotamiasCVPR 2025
- Spatial-Temporal Parallel Transformer for Arm-Hand Dynamic EstimationShuying Liu, Wenbin Wu, Jiaxian Wu, Yue LinCVPR 2022 · 9 citations
- HumanBA: Human-Aware Bundle Adjustment via Global Human-Camera DecouplingFengyuan Yang, Tanuj Sur, Tze Ho Elden Tse, Angela YaoCVPR 2026
- Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single VideoDavid Yifan Yao, Albert J. Zhai, Shenlong WangCVPR 2025
