OnlineHMR: Video-based Online World-Grounded Human Mesh Recovery
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910057759768576 |
|---|---|
| author | Zhao, Yiwen Zheng, Ce Wang, Yufu Yang, Hsueh-Han Daniel Wen, Liting Jeni, Laszlo A. |
| author_facet | Zhao, Yiwen Zheng, Ce Wang, Yufu Yang, Hsueh-Han Daniel Wen, Liting Jeni, Laszlo A. |
| contents | Human mesh recovery (HMR) models 3D human body from monocular videos, with recent works extending it to world-coordinate human trajectory and motion reconstruction. However, most existing methods remain offline, relying on future frames or global optimization, which limits their applicability in interactive feedback and perception-action loop scenarios such as AR/VR and telepresence. To address this, we propose OnlineHMR, a fully online framework that jointly satisfies four essential criteria of online processing, including system-level causality, faithfulness, temporal consistency, and efficiency. Built upon a two-branch architecture, OnlineHMR enables streaming inference via a causal key-value cache design and a curated sliding-window learning strategy. Meanwhile, a human-centric incremental SLAM provides online world-grounded alignment under physically plausible trajectory correction. Experimental results show that our method achieves performance comparable to existing chunk-based approaches on the standard EMDB benchmark and highly dynamic custom videos, while uniquely supporting online processing. Page and code are available at https://tsukasane.github.io/Video-OnlineHMR/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_17355 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OnlineHMR: Video-based Online World-Grounded Human Mesh Recovery Zhao, Yiwen Zheng, Ce Wang, Yufu Yang, Hsueh-Han Daniel Wen, Liting Jeni, Laszlo A. Computer Vision and Pattern Recognition Human mesh recovery (HMR) models 3D human body from monocular videos, with recent works extending it to world-coordinate human trajectory and motion reconstruction. However, most existing methods remain offline, relying on future frames or global optimization, which limits their applicability in interactive feedback and perception-action loop scenarios such as AR/VR and telepresence. To address this, we propose OnlineHMR, a fully online framework that jointly satisfies four essential criteria of online processing, including system-level causality, faithfulness, temporal consistency, and efficiency. Built upon a two-branch architecture, OnlineHMR enables streaming inference via a causal key-value cache design and a curated sliding-window learning strategy. Meanwhile, a human-centric incremental SLAM provides online world-grounded alignment under physically plausible trajectory correction. Experimental results show that our method achieves performance comparable to existing chunk-based approaches on the standard EMDB benchmark and highly dynamic custom videos, while uniquely supporting online processing. Page and code are available at https://tsukasane.github.io/Video-OnlineHMR/. |
| title | OnlineHMR: Video-based Online World-Grounded Human Mesh Recovery |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.17355 |