PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912827903574016 |
|---|---|
| author | Zhang, Qiyuan Gong, Biao Tan, Shuai Zhang, Zheng Shen, Yujun Zhu, Xing Li, Yuyuan Yao, Kelu Shen, Chunhua Zou, Changqing |
| author_facet | Zhang, Qiyuan Gong, Biao Tan, Shuai Zhang, Zheng Shen, Yujun Zhu, Xing Li, Yuyuan Yao, Kelu Shen, Chunhua Zou, Changqing |
| contents | Physical principles are fundamental to realistic visual simulation, but remain a significant oversight in transformer-based video generation. This gap highlights a critical limitation in rendering rigid body motion, a core tenet of classical mechanics. While computer graphics and physics-based simulators can easily model such collisions using Newton formulas, modern pretrain-finetune paradigms discard the concept of object rigidity during pixel-level global denoising. Even perfectly correct mathematical constraints are treated as suboptimal solutions (i.e., conditions) during model optimization in post-training, fundamentally limiting the physical realism of generated videos. Motivated by these considerations, we introduce, for the first time, a physics-aware reinforcement learning paradigm for video generation models that enforces physical collision rules directly in high-dimensional spaces, ensuring the physics knowledge is strictly applied rather than treated as conditions. Subsequently, we extend this paradigm to a unified framework, termed Mimicry-Discovery Cycle (MDcycle), which allows substantial fine-tuning while fully preserving the model's ability to leverage physics-grounded feedback. To validate our approach, we construct new benchmark PhysRVGBench and perform extensive qualitative and quantitative experiments to thoroughly assess its effectiveness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_11087 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models Zhang, Qiyuan Gong, Biao Tan, Shuai Zhang, Zheng Shen, Yujun Zhu, Xing Li, Yuyuan Yao, Kelu Shen, Chunhua Zou, Changqing Computer Vision and Pattern Recognition Physical principles are fundamental to realistic visual simulation, but remain a significant oversight in transformer-based video generation. This gap highlights a critical limitation in rendering rigid body motion, a core tenet of classical mechanics. While computer graphics and physics-based simulators can easily model such collisions using Newton formulas, modern pretrain-finetune paradigms discard the concept of object rigidity during pixel-level global denoising. Even perfectly correct mathematical constraints are treated as suboptimal solutions (i.e., conditions) during model optimization in post-training, fundamentally limiting the physical realism of generated videos. Motivated by these considerations, we introduce, for the first time, a physics-aware reinforcement learning paradigm for video generation models that enforces physical collision rules directly in high-dimensional spaces, ensuring the physics knowledge is strictly applied rather than treated as conditions. Subsequently, we extend this paradigm to a unified framework, termed Mimicry-Discovery Cycle (MDcycle), which allows substantial fine-tuning while fully preserving the model's ability to leverage physics-grounded feedback. To validate our approach, we construct new benchmark PhysRVGBench and perform extensive qualitative and quantitative experiments to thoroughly assess its effectiveness. |
| title | PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.11087 |