The paper introduces JoHan, a generative framework that directly recovers 2D and 3D hand motion from video sequences without intermediate per‑frame pose predictions. By jointly learning temporal dynamics and 2D‑3D correspondence, JoHan generates aligned pose sequences that improve temporal consistency and enable accurate estimation of the hand’s global position and orientation relative to the camera. Experiments on challenging benchmarks show that JoHan achieves higher accuracy and faster performance, producing smoother hand‑motion dynamics while maintaining high per‑frame pose accuracy.
By Chen Xu, Yunqi Li, Binbin Huang, Brent Yi, Shenghua Gao, Yi Ma
arXiv:2601.13913v3 Announce Type: replace
Abstract: We consider monocular 3D human pose estimation (HPE), where the goal is to predict 3D human skeletal joints from a single 2D image, typically via 2...
By Pavlo Melnyk, Cuong Le, Urs Waldmann, Per-Erik Forss\'en, Bastian Wandt
Accurate monocular 4D hand reconstruction remains challenging. Per-frame discriminative regressors lack temporal context and often produce jittery predictions.
arXiv:2607. 11221v1 Announce Type: cross Abstract: Accurate monocular 4D hand reconstruction remains challenging.
By Mingxi Xu, Bowen Duan, Yi Gu, Zhengyang Shen, Renjing Xu, Yutao Yue
Robotic manipulation with dexterous hands is a cornerstone of Embodied AI, yet its progress is stifled by the high cost of collecting embodiment-aware teleoperation data. While abundant egocentric videos of human hands offer a scalable alternative, the profound discrepancies in appearance, articulation, and camera viewpoints between human and robotic data raise significant challenges for co-training.
Driven by the availability of large-scale datasets, Human Pose Estimation (HPE) plays a critical role in numerous downstream tasks. However, mainstream benchmarks exhibit severe representation bias, predominantly featuring able-bodied individuals.
arXiv:2609.24424v1 Announce Type: new
Abstract: Monocular RGB-based hand pose estimation has emerged as a critical research frontier in computer vision. The local hand pose estimation methods predict...
By Kaiwen Ren, Yiran Jiang, Yongjing Ye, Shihong Xia
KAD-Net introduces a Kinematics-Aware Decoupled Learning Network for 3D hand pose estimation from a single depth image. It employs a Finger Topology Constraint module that uses local kinematic representations of three consecutive finger joints to better model distal joint relationships and handle occlusion. The architecture also decouples 2D joint localization from depth estimation in a hierarchical multitask framework, reducing feature interference and improving accuracy on benchmark datasets such as ICVL, NYU, and MSRA.
By Jun Lu, Zhenming Chen, Lin Chen, Kanlun Tan, Xiaoling Li, Qiao Liu
arXiv:2606.19156v2 Announce Type: replace
Abstract: Dynamic 3D hand reconstruction from egocentric videos is essential for next-generation computing platforms such as AR/VR and AI glasses. Despite it...
By Jeongmin Bae, Seoha Kim, Marc Pollefeys, Mahdi Rad, Youngjung Uh, Taein Kwon
arXiv:2606. 10902v1 Announce Type: cross Abstract: Subject Customization is a foundational task in modern image generation.
By Xuan Han, Yihao Zhao, Mingyu You
arXiv:2507. 12138v2 Announce Type: replace-cross Abstract: We introduce a principled, data-driven approach for modeling a neural prior over human body poses using normalizing flows.
By Michal Heker, Sefy Kagarlitsky, David Tolpin
arXiv:2609.36937v1 Announce Type: cross
Abstract: Human image animation aims to transfer motion from a driving video to subjects in a reference image. Despite remarkable progress in video generation,...
By Sangeyl Lee, Seunghyun Shin, Seungho Park, Wooseok Jeon, Hae-Gon Jeon