TROPHIES: Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910282130915328 |
|---|---|
| author | Liu, Jinpeng Xu, Yukang Li, Yutong Liu, Xingyu |
| author_facet | Liu, Jinpeng Xu, Yukang Li, Yutong Liu, Xingyu |
| contents | Reconstructing humans and their surrounding environments in a globally consistent 4D space is essential for comprehensive perception. However, prior works typically assume single-view inputs or decouple humans, scenes, and cameras, making them unable to recover coherent geometry, stable motion, and physically aligned trajectories. These limitations motivate us to introduce a new task: unified human-scene-camera reconstruction from multi-view videos, which aims to jointly estimate dynamic humans, static scenes, and camera poses in one global coordinate frame. We propose TROPHIES--Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos-a unified framework tailored for this task. TROPHIES features a Human Branch that models humans through temporal and spatial reasoning, and a Scene Branch that reconstructs static geometry with human-aware attention. A global alignment and optimization module couples both branches by enforcing scale consistency, contact priors, and cross-view temporal coherence. Experiments on EgoHuman and EgoExo4D demonstrate that TROPHIES achieves globally aligned, physically plausible 4D reconstructions and consistently outperforms existing paradigms in both global fidelity and human-scene consistency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_02350 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TROPHIES: Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos Liu, Jinpeng Xu, Yukang Li, Yutong Liu, Xingyu Computer Vision and Pattern Recognition Reconstructing humans and their surrounding environments in a globally consistent 4D space is essential for comprehensive perception. However, prior works typically assume single-view inputs or decouple humans, scenes, and cameras, making them unable to recover coherent geometry, stable motion, and physically aligned trajectories. These limitations motivate us to introduce a new task: unified human-scene-camera reconstruction from multi-view videos, which aims to jointly estimate dynamic humans, static scenes, and camera poses in one global coordinate frame. We propose TROPHIES--Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos-a unified framework tailored for this task. TROPHIES features a Human Branch that models humans through temporal and spatial reasoning, and a Scene Branch that reconstructs static geometry with human-aware attention. A global alignment and optimization module couples both branches by enforcing scale consistency, contact priors, and cross-view temporal coherence. Experiments on EgoHuman and EgoExo4D demonstrate that TROPHIES achieves globally aligned, physically plausible 4D reconstructions and consistently outperforms existing paradigms in both global fidelity and human-scene consistency. |
| title | TROPHIES: Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2606.02350 |