BridgeV2W: Bridging Video Generation Models to Embodied World Models via Embodiment Masks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908809833742336 |
|---|---|
| author | Chen, Yixiang Li, Peiyan Yang, Jiabing He, Keji Wu, Xiangnan Xu, Yuan Wang, Kai Liu, Jing Liu, Nianfeng Huang, Yan Wang, Liang |
| author_facet | Chen, Yixiang Li, Peiyan Yang, Jiabing He, Keji Wu, Xiangnan Xu, Yuan Wang, Kai Liu, Jing Liu, Nianfeng Huang, Yan Wang, Liang |
| contents | Embodied world models have emerged as a promising paradigm in robotics, most of which leverage large-scale Internet videos or pretrained video generation models to enrich visual and motion priors. However, they still face key challenges: a misalignment between coordinate-space actions and pixel-space videos, sensitivity to camera viewpoint, and non-unified architectures across embodiments. To this end, we present BridgeV2W, which converts coordinate-space actions into pixel-aligned embodiment masks rendered from the URDF and camera parameters. These masks are then injected into a pretrained video generation model via a ControlNet-style pathway, which aligns the action control signals with predicted videos, adds view-specific conditioning to accommodate camera viewpoints, and yields a unified world model architecture across embodiments. To mitigate overfitting to static backgrounds, BridgeV2W further introduces a flow-based motion loss that focuses on learning dynamic and task-relevant regions. Experiments on single-arm (DROID) and dual-arm (AgiBot-G1) datasets, covering diverse and challenging conditions with unseen viewpoints and scenes, show that BridgeV2W improves video generation quality compared to prior state-of-the-art methods. We further demonstrate the potential of BridgeV2W on downstream real-world tasks, including policy evaluation and goal-conditioned planning. More results can be found on our project website at https://BridgeV2W.github.io . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03793 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | BridgeV2W: Bridging Video Generation Models to Embodied World Models via Embodiment Masks Chen, Yixiang Li, Peiyan Yang, Jiabing He, Keji Wu, Xiangnan Xu, Yuan Wang, Kai Liu, Jing Liu, Nianfeng Huang, Yan Wang, Liang Robotics Computer Vision and Pattern Recognition Embodied world models have emerged as a promising paradigm in robotics, most of which leverage large-scale Internet videos or pretrained video generation models to enrich visual and motion priors. However, they still face key challenges: a misalignment between coordinate-space actions and pixel-space videos, sensitivity to camera viewpoint, and non-unified architectures across embodiments. To this end, we present BridgeV2W, which converts coordinate-space actions into pixel-aligned embodiment masks rendered from the URDF and camera parameters. These masks are then injected into a pretrained video generation model via a ControlNet-style pathway, which aligns the action control signals with predicted videos, adds view-specific conditioning to accommodate camera viewpoints, and yields a unified world model architecture across embodiments. To mitigate overfitting to static backgrounds, BridgeV2W further introduces a flow-based motion loss that focuses on learning dynamic and task-relevant regions. Experiments on single-arm (DROID) and dual-arm (AgiBot-G1) datasets, covering diverse and challenging conditions with unseen viewpoints and scenes, show that BridgeV2W improves video generation quality compared to prior state-of-the-art methods. We further demonstrate the potential of BridgeV2W on downstream real-world tasks, including policy evaluation and goal-conditioned planning. More results can be found on our project website at https://BridgeV2W.github.io . |
| title | BridgeV2W: Bridging Video Generation Models to Embodied World Models via Embodiment Masks |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.03793 |