PhyGDPO: Physics-Aware Groupwise Direct Preference
Optimization for Physically Consistent Text-to-Video Generation

(1) A gymnast drops from the parallel bars and lands safely on the mat below.
Ours	OpenAI Sora2	Google Veo3.1
(2) A soccer player runs, plants their foot, and drop kicks a soccer ball high into the air, the ball arcing visibly.
Ours	OpenAI Sora2	Google Veo3.1
(3) A person wearing a helmet performs a handspring over a platform.
Ours	OpenAI Sora2	Google Veo3.1
(4) A person plays squash on an indoor court.
Ours	OpenAI Sora2	Google Veo3.1

 

Introduction

This is a re-implementation of our work "PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation" using public datasets and re-trained model based on public codes. In this work, we present a data construction pipeline, PhyAugPipe, that can create data pairs and a new direct preference optimization framework, PhyGDPO, for physically plausile text-to-video generation. If you find our repo useful, please give it a star ⭐ and consider citing our paper. Thank you :)

 

Figure 1: Our data construction pipeline

 

Figure 2: The overall framework of our OmniVCus

News

• 2025.12.31 : Our paper is on arxiv now. Code, data, and models will be made publicly available, stay tuned. 🚀
• 2025.12.31 : Our project page has been built up. Feel free to check the video generation results on the project page.

Citation

If you find our repo useful, please consider citing our paper:

@article{cai2025phygdpo,
  title={PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation},
  author={Cai, Yuanhao and Li, Kunpeng and Jia, Menglin and Wang, Jialiang and Sun, Junzhe and Liang, Feng and Chen, Weifeng and Juefei-Xu, Felix and Wang, Chu and Thabet, Ali and others},
  journal={arXiv preprint arXiv:2512.24551},
  year={2025}
}