Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.18173 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911282600345600 |
|---|---|
| author | Pallotta, Enrico Azar, Sina Mokhtarzadeh Doorenbos, Lars Ozsoy, Serdar Iqbal, Umar Gall, Juergen |
| author_facet | Pallotta, Enrico Azar, Sina Mokhtarzadeh Doorenbos, Lars Ozsoy, Serdar Iqbal, Umar Gall, Juergen |
| contents | Egocentric video generation with fine-grained control through body motion is a key requirement towards embodied AI agents that can simulate, predict, and plan actions. In this work, we propose EgoControl, a pose-controllable video diffusion model trained on egocentric data. We train a video prediction model to condition future frame generation on explicit 3D body pose sequences. To achieve precise motion control, we introduce a novel pose representation that captures both global camera dynamics and articulated body movements, and integrate it through a dedicated control mechanism within the diffusion process. Given a short sequence of observed frames and a sequence of target poses, EgoControl generates temporally coherent and visually realistic future frames that align with the provided pose control. Experimental results demonstrate that EgoControl produces high-quality, pose-consistent egocentric videos, paving the way toward controllable embodied video simulation and understanding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_18173 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses Pallotta, Enrico Azar, Sina Mokhtarzadeh Doorenbos, Lars Ozsoy, Serdar Iqbal, Umar Gall, Juergen Computer Vision and Pattern Recognition Egocentric video generation with fine-grained control through body motion is a key requirement towards embodied AI agents that can simulate, predict, and plan actions. In this work, we propose EgoControl, a pose-controllable video diffusion model trained on egocentric data. We train a video prediction model to condition future frame generation on explicit 3D body pose sequences. To achieve precise motion control, we introduce a novel pose representation that captures both global camera dynamics and articulated body movements, and integrate it through a dedicated control mechanism within the diffusion process. Given a short sequence of observed frames and a sequence of target poses, EgoControl generates temporally coherent and visually realistic future frames that align with the provided pose control. Experimental results demonstrate that EgoControl produces high-quality, pose-consistent egocentric videos, paving the way toward controllable embodied video simulation and understanding. |
| title | EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.18173 |