EgoHand: Monocular 3D Hand Reconstruction from Egocentric Video
Computer Science > Computer Vision and Pattern Recognition arXiv:2610.30293 (cs) [Submitted on 21 Oct 2026] Title: EgoHand: Monocular 3D Hand Reconstruction from Egocentric Video Authors: Chao-Yeh Chen, Tiffany Chen, Lin Duan, Tianyi Hu, Yu-Hsiang Huang, Umar Iqbal, Jiefeng Li, Edy Lim, Yanchen Liu, Yihan Pang, Hang Qiu, Jun Saito, Shao Su, Qingsi Wang, Xiufeng Xie.
计算机科学 > 计算机视觉与模式识别 arXiv:2610.30293 (cs) [提交于 2026 年 10 月 21 日] 标题：EgoHand：基于第一人称视频的单目 3D 手部重建。作者：Chao-Yeh Chen, Tiffany Chen, Lin Duan, Tianyi Hu, Yu-Hsiang Huang, Umar Iqbal, Jiefeng Li, Edy Lim, Yanchen Liu, Yihan Pang, Hang Qiu, Jun Saito, Shao Su, Qingsi Wang, Xiufeng Xie。
Abstract: We introduce EgoHand, a monocular 3D hand reconstruction model that achieves state-of-the-art performance on egocentric video. Central to our approach is the curation of a high-quality training corpus of 14 million images, combining synthetic data, in-the-wild video, and multi-camera motion capture to balance scene diversity and supervision quality.
摘要：我们介绍了 EgoHand，这是一种在第一人称视频上实现最先进性能的单目 3D 手部重建模型。我们方法的核心是策划了一个包含 1400 万张图像的高质量训练语料库，结合了合成数据、野外视频和多摄像机动作捕捉，以平衡场景多样性和监督质量。
The model adopts SOMA-Hand as its parametric representation and processes 2D hand crops with a transformer encoder, incorporating camera cues and an auxiliary 2D branch to improve geometric consistency and image alignment. Zero-shot evaluations on HOT3D, ARCTIC, and H2O demonstrate strong out-of-domain generalization, with lower joint-position, root-translation, and acceleration errors than competing baselines at an inference latency of approximately 9.69 ms.
该模型采用 SOMA-Hand 作为其参数化表示，并使用 Transformer 编码器处理 2D 手部裁剪图像，同时结合摄像机线索和辅助 2D 分支，以提高几何一致性和图像对齐效果。在 HOT3D、ARCTIC 和 H2O 上的零样本评估证明了其强大的域外泛化能力，在约 9.69 毫秒的推理延迟下，其关节位置、根部平移和加速度误差均低于竞争基准。
A blinded user preference study further shows that participants favor EgoHand’s reconstructed hand poses over those from Apple EgoDex and Ropedia Xperience-10M. We release the EgoHand model and source code under the OpenMDW license, allowing free commercial use of the model.
一项盲测用户偏好研究进一步表明，参与者更倾向于 EgoHand 重建的手部姿势，而非 Apple EgoDex 和 Ropedia Xperience-10M 的结果。我们根据 OpenMDW 许可证发布了 EgoHand 模型和源代码，允许该模型的免费商业使用。