PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis

🔗 Links

• 📄 arXiv Paper
• 💻 Project

🏗️ Architecture

PhysGM Architecture Overview

🚀 Key Features

• ⚡ Fast Generation: Generate 4D simulations from single images in under 1 minute
• 🎯 High Fidelity: Realistic physics simulation with accurate material properties
• 🔄 End-to-End: Joint prediction of 3D Gaussians and physics parameters
• 📊 Large Dataset: Trained on PhysAssets with 24,000+ annotated 3D assets
• 🎨 Versatile: Handles various scenarios including dropping, stretching, and multi-object interactions

📚 Citation

If you find our work useful, please cite our paper:

@misc{lv2025physgmlargephysicalgaussian,
  title={PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis}, 
  author={Chunji Lv and Zequn Chen and Donglin Di and Weinan Zhang and Hao Li and Wei Chen and Changsheng Li},
  year={2025},
  eprint={2508.13911},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2508.13911}, 
}

---

⭐ If you like this project, please give it a star! ⭐

Made with ❤️ by the PhysGM Team