OrthoPhys: Physically Plausible Video Generation with Orthogonal-View Geometry Guidance
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916044295110656 |
|---|---|
| author | Wang, Cong Zhu, Hanxin Tang, Xiao Luo, Jiayi Jin, Xin Chen, Long Chen, Zhibo |
| author_facet | Wang, Cong Zhu, Hanxin Tang, Xiao Luo, Jiayi Jin, Xin Chen, Long Chen, Zhibo |
| contents | Recent progress in video generation has led to substantial improvements in visual fidelity, yet ensuring physically consistent motion remains a fundamental challenge. Intuitively, this limitation can be attributed to the fact that real-world object motion unfolds in three-dimensional space, while video observations provide only partial, view-dependent projections of such dynamics. To address these issues, we propose OrthoPhys, a two-stage framework that leverages orthogonal-view geometry guidance to enforce physical plausibility. Instead of directly generating unstructured 2D videos, our first stage generates synchronized, four-view orthogonal videos of the foreground dynamics. By incorporating a geometry-enhanced attention mechanism across these orthogonal views, this stage effectively enforces 3D spatial coherence and implicitly grounds the motion in physical attributes. In the second stage, these physically consistent orthogonal foregrounds serve as rigid guidance to synthesize the final complete video, seamlessly learning the interaction between foreground dynamics and the background context. To support this orthogonal-view training paradigm, we construct PhysMV, a dataset containing 40K scenes, each consisting of four orthogonal viewpoints, resulting in a total of 160K video sequences. Extensive experiments demonstrate that OrthoPhys significantly improves physical realism and spatial-temporal coherence over existing video generation methods. Project page: https://anonymous.4open.science/w/Phys4D/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_18639 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OrthoPhys: Physically Plausible Video Generation with Orthogonal-View Geometry Guidance Wang, Cong Zhu, Hanxin Tang, Xiao Luo, Jiayi Jin, Xin Chen, Long Chen, Zhibo Computer Vision and Pattern Recognition Recent progress in video generation has led to substantial improvements in visual fidelity, yet ensuring physically consistent motion remains a fundamental challenge. Intuitively, this limitation can be attributed to the fact that real-world object motion unfolds in three-dimensional space, while video observations provide only partial, view-dependent projections of such dynamics. To address these issues, we propose OrthoPhys, a two-stage framework that leverages orthogonal-view geometry guidance to enforce physical plausibility. Instead of directly generating unstructured 2D videos, our first stage generates synchronized, four-view orthogonal videos of the foreground dynamics. By incorporating a geometry-enhanced attention mechanism across these orthogonal views, this stage effectively enforces 3D spatial coherence and implicitly grounds the motion in physical attributes. In the second stage, these physically consistent orthogonal foregrounds serve as rigid guidance to synthesize the final complete video, seamlessly learning the interaction between foreground dynamics and the background context. To support this orthogonal-view training paradigm, we construct PhysMV, a dataset containing 40K scenes, each consisting of four orthogonal viewpoints, resulting in a total of 160K video sequences. Extensive experiments demonstrate that OrthoPhys significantly improves physical realism and spatial-temporal coherence over existing video generation methods. Project page: https://anonymous.4open.science/w/Phys4D/. |
| title | OrthoPhys: Physically Plausible Video Generation with Orthogonal-View Geometry Guidance |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.18639 |