cs.CVNov 16, 2026

MetricHand: Geometry-Aware Flow Matching for 4D Hand Reconstruction in Metric World Space

Authors: Yibo Bai, Likui Zhang, Jinglei Zhang, Zhengbin Pang, Xingshen Song, Xiaoqing Yin, Jinsheng Deng

Organizations: National University of Defense Technology · Sun Yat-sen University · Shanghai Jiao Tong University · Academy of Military Sciences

Abstract

Egocentric hand motion provides physical motion supervision for dexterous manipulation and vision-language-action pretraining. Reliable use of this supervision requires accurate and temporally coherent 4D hand reconstruction in metric world space. Existing methods typically lift framewise estimates produced under weak perspective into world coordinates. By ignoring joint-dependent depth variation at close range, this approximation couples errors in translation, orientation, and articulation that persist after world lifting and worsen under occlusion. We present MetricHand, a geometry-aware flow matching framework for 4D hand reconstruction in metric world space. MetricHand encodes depth priors from hand-object interaction regions into joint-associated representations that preserve local spatial structure and metric scale. Fused with visual features, this geometry guides coarse metric estimation and conditions every step of temporal generation. The model jointly recovers world-space translation, global orientation, MANO articulation, and shape, while structural priors and temporal context support estimation under partial occlusion. MetricHand reduces camera-space MPJPE by 49.3% and 52.9%, absolute world-space MPJPE by 28.7% and 21.7%, and wrist localization error by 48.5% and 37.9% relative to HaWoR, respectively. World-space acceleration error decreases by 44.2% and 64.3%, demonstrating improved temporal fidelity alongside more accurate absolute localization.

Figures & tables

Explore similar work

CardsList
  1. DewHand: Direct Metric World-Space Hand Motion Reconstruction from Egocentric Videos

    Oct 21, 2026Naru Suzuki, Satoshi Ikehata, Takehiko Ohkawa +23D Hand ReconstructionEgocentric Video Understanding

  2. HandFlow: Fully Generative 4D Hand Recovery with Flow Matching

    Jul 13, 2026Mingxi Xu, Bowen Duan, Yi Gu +3Articulated Object Reconstruction4D Reconstruction

  3. StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video

    May 18, 2026Huajian Zeng, Chaohua Yao, Yuantai Zhang +3Flow Matching3D Hand Pose Estimation