BioHuman: Learning Biomechanical Human Representations from Video
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918501623529472 |
|---|---|
| author | Huo, Yujun Zhang, He Song, Chentao Song, Honglin Zuo, Zongyu Yu, Tao |
| author_facet | Huo, Yujun Zhang, He Song, Chentao Song, Honglin Zuo, Zongyu Yu, Tao |
| contents | Understanding human motion beyond surface kinematics is crucial for motion analysis, rehabilitation, and injury risk assessment. However, progress in this domain is limited by the lack of large-scale datasets with biomechanical annotations, and by existing approaches that cannot directly infer internal biomechanical states from visual observations. In this paper, we introduce a simulation-based framework for estimating muscle activations from existing motion capture datasets, resulting in BioHuman10M, a large-scale dataset with synchronized video, motion, and activations. Building on BioHuman10M, we propose BioHuman, an end-to-end model that takes monocular video as input and jointly predicts human motion and muscle activations, effectively bridging visual observations and internal biomechanical states. Extensive experiments demonstrate that BioHuman enables accurate reconstruction of both kinematic motion and muscle activity, and generalizes across diverse subjects and motions. We believe our approach establishes a new benchmark for video-based biomechanical understanding and opens up new possibilities for physically grounded human modeling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_14772 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | BioHuman: Learning Biomechanical Human Representations from Video Huo, Yujun Zhang, He Song, Chentao Song, Honglin Zuo, Zongyu Yu, Tao Computer Vision and Pattern Recognition Graphics Machine Learning Understanding human motion beyond surface kinematics is crucial for motion analysis, rehabilitation, and injury risk assessment. However, progress in this domain is limited by the lack of large-scale datasets with biomechanical annotations, and by existing approaches that cannot directly infer internal biomechanical states from visual observations. In this paper, we introduce a simulation-based framework for estimating muscle activations from existing motion capture datasets, resulting in BioHuman10M, a large-scale dataset with synchronized video, motion, and activations. Building on BioHuman10M, we propose BioHuman, an end-to-end model that takes monocular video as input and jointly predicts human motion and muscle activations, effectively bridging visual observations and internal biomechanical states. Extensive experiments demonstrate that BioHuman enables accurate reconstruction of both kinematic motion and muscle activity, and generalizes across diverse subjects and motions. We believe our approach establishes a new benchmark for video-based biomechanical understanding and opens up new possibilities for physically grounded human modeling. |
| title | BioHuman: Learning Biomechanical Human Representations from Video |
| topic | Computer Vision and Pattern Recognition Graphics Machine Learning |
| url | https://arxiv.org/abs/2605.14772 |