PhysInOne: Visual Physics Learning and Reasoning in One Suite
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915930276102144 |
|---|---|
| author | Zhou, Siyuan Wang, Hejun Cheng, Hu Li, Jinxi Wang, Dongsheng Jiang, Junwei Jin, Yixiao Huang, Jiayue Mao, Shiwei Liu, Shangjia Yang, Yafei Song, Hongkang Wei, Shenxing Zhang, Zihui Huang, Peng Liu, Shijie Hao, Zhengli Li, Hao Li, Yitian Zhou, Wenqi Zhao, Zhihan He, Zongqi Wen, Hongtao Huang, Shouwang Yun, Peng Cheng, Bowen Fu, Pok Kazaf Lai, Wai Kit Chen, Jiahao Wang, Kaiyuan Sun, Zhixuan Li, Ziqi Hu, Haochen Zhang, Di Yuen, Chun Ho Wang, Bing Wang, Zhihua Zou, Chuhang Yang, Bo |
| author_facet | Zhou, Siyuan Wang, Hejun Cheng, Hu Li, Jinxi Wang, Dongsheng Jiang, Junwei Jin, Yixiao Huang, Jiayue Mao, Shiwei Liu, Shangjia Yang, Yafei Song, Hongkang Wei, Shenxing Zhang, Zihui Huang, Peng Liu, Shijie Hao, Zhengli Li, Hao Li, Yitian Zhou, Wenqi Zhao, Zhihan He, Zongqi Wen, Hongtao Huang, Shouwang Yun, Peng Cheng, Bowen Fu, Pok Kazaf Lai, Wai Kit Chen, Jiahao Wang, Kaiyuan Sun, Zhixuan Li, Ziqi Hu, Haochen Zhang, Di Yuen, Chun Ho Wang, Bing Wang, Zhihua Zou, Chuhang Yang, Bo |
| contents | We present PhysInOne, a large-scale synthetic dataset addressing the critical scarcity of physically-grounded training data for AI systems. Unlike existing datasets limited to merely hundreds or thousands of examples, PhysInOne provides 2 million videos across 153,810 dynamic 3D scenes, covering 71 basic physical phenomena in mechanics, optics, fluid dynamics, and magnetism. Distinct from previous works, our scenes feature multiobject interactions against complex backgrounds, with comprehensive ground-truth annotations including 3D geometry, semantics, dynamic motion, physical properties, and text descriptions. We demonstrate PhysInOne's efficacy across four emerging applications: physics-aware video generation, long-/short-term future frame prediction, physical property estimation, and motion transfer. Experiments show that fine-tuning foundation models on PhysInOne significantly enhances physical plausibility, while also exposing critical gaps in modeling complex physical dynamics and estimating intrinsic properties. As the largest dataset of its kind, orders of magnitude beyond prior works, PhysInOne establishes a new benchmark for advancing physics-grounded world models in generation, simulation, and embodied AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09415 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PhysInOne: Visual Physics Learning and Reasoning in One Suite Zhou, Siyuan Wang, Hejun Cheng, Hu Li, Jinxi Wang, Dongsheng Jiang, Junwei Jin, Yixiao Huang, Jiayue Mao, Shiwei Liu, Shangjia Yang, Yafei Song, Hongkang Wei, Shenxing Zhang, Zihui Huang, Peng Liu, Shijie Hao, Zhengli Li, Hao Li, Yitian Zhou, Wenqi Zhao, Zhihan He, Zongqi Wen, Hongtao Huang, Shouwang Yun, Peng Cheng, Bowen Fu, Pok Kazaf Lai, Wai Kit Chen, Jiahao Wang, Kaiyuan Sun, Zhixuan Li, Ziqi Hu, Haochen Zhang, Di Yuen, Chun Ho Wang, Bing Wang, Zhihua Zou, Chuhang Yang, Bo Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics We present PhysInOne, a large-scale synthetic dataset addressing the critical scarcity of physically-grounded training data for AI systems. Unlike existing datasets limited to merely hundreds or thousands of examples, PhysInOne provides 2 million videos across 153,810 dynamic 3D scenes, covering 71 basic physical phenomena in mechanics, optics, fluid dynamics, and magnetism. Distinct from previous works, our scenes feature multiobject interactions against complex backgrounds, with comprehensive ground-truth annotations including 3D geometry, semantics, dynamic motion, physical properties, and text descriptions. We demonstrate PhysInOne's efficacy across four emerging applications: physics-aware video generation, long-/short-term future frame prediction, physical property estimation, and motion transfer. Experiments show that fine-tuning foundation models on PhysInOne significantly enhances physical plausibility, while also exposing critical gaps in modeling complex physical dynamics and estimating intrinsic properties. As the largest dataset of its kind, orders of magnitude beyond prior works, PhysInOne establishes a new benchmark for advancing physics-grounded world models in generation, simulation, and embodied AI. |
| title | PhysInOne: Visual Physics Learning and Reasoning in One Suite |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics |
| url | https://arxiv.org/abs/2604.09415 |