WATCH: World-aware Allied Trajectory and pose reconstruction for Camera and Human
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908519946518528 |
|---|---|
| author | Ying, Qijun Hu, Zhongyuan Zhang, Rui Li, Ronghui Lu, Yu Zeng, Zijiao |
| author_facet | Ying, Qijun Hu, Zhongyuan Zhang, Rui Li, Ronghui Lu, Yu Zeng, Zijiao |
| contents | Global human motion reconstruction from in-the-wild monocular videos is increasingly demanded across VR, graphics, and robotics applications, yet requires accurate mapping of human poses from camera to world coordinates-a task challenged by depth ambiguity, motion ambiguity, and the entanglement between camera and human movements. While human-motion-centric approaches excel in preserving motion details and physical plausibility, they suffer from two critical limitations: insufficient exploitation of camera orientation information and ineffective integration of camera translation cues. We present WATCH (World-aware Allied Trajectory and pose reconstruction for Camera and Human), a unified framework addressing both challenges. Our approach introduces an analytical heading angle decomposition technique that offers superior efficiency and extensibility compared to existing geometric methods. Additionally, we design a camera trajectory integration mechanism inspired by world models, providing an effective pathway for leveraging camera translation information beyond naive hard-decoding approaches. Through experiments on in-the-wild benchmarks, WATCH achieves state-of-the-art performance in end-to-end trajectory reconstruction. Our work demonstrates the effectiveness of jointly modeling camera-human motion relationships and offers new insights for addressing the long-standing challenge of camera translation integration in global human motion reconstruction. The code will be available publicly. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_04600 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WATCH: World-aware Allied Trajectory and pose reconstruction for Camera and Human Ying, Qijun Hu, Zhongyuan Zhang, Rui Li, Ronghui Lu, Yu Zeng, Zijiao Computer Vision and Pattern Recognition Global human motion reconstruction from in-the-wild monocular videos is increasingly demanded across VR, graphics, and robotics applications, yet requires accurate mapping of human poses from camera to world coordinates-a task challenged by depth ambiguity, motion ambiguity, and the entanglement between camera and human movements. While human-motion-centric approaches excel in preserving motion details and physical plausibility, they suffer from two critical limitations: insufficient exploitation of camera orientation information and ineffective integration of camera translation cues. We present WATCH (World-aware Allied Trajectory and pose reconstruction for Camera and Human), a unified framework addressing both challenges. Our approach introduces an analytical heading angle decomposition technique that offers superior efficiency and extensibility compared to existing geometric methods. Additionally, we design a camera trajectory integration mechanism inspired by world models, providing an effective pathway for leveraging camera translation information beyond naive hard-decoding approaches. Through experiments on in-the-wild benchmarks, WATCH achieves state-of-the-art performance in end-to-end trajectory reconstruction. Our work demonstrates the effectiveness of jointly modeling camera-human motion relationships and offers new insights for addressing the long-standing challenge of camera translation integration in global human motion reconstruction. The code will be available publicly. |
| title | WATCH: World-aware Allied Trajectory and pose reconstruction for Camera and Human |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.04600 |