KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#dsh #dsh-plugin #ai-agents #developer-tools #typescript #codex #claude-code #mcp #rust #deepseek-harness #ai-agent #cli

PSIVG

★ 137 Open GitHub ↗

[CVPR 2026] Physical Simulator In-the-Loop Video Generation

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# [CVPR 2026] Physical Simulator In-the-Loop Video Generation

<div>
 
 <a href="https://lingeng.foo/" target="_blank" rel="noopener noreferrer">Lin Geng
 Foo</a>1,5,
 
 
 <a href="https://markhh.com/" target="_blank" rel="noopener noreferrer">Mark He
 Huang</a>2,3,
 
 
 <a href="https://alexlattas.com/" target="_blank" rel="noopener noreferrer">Alexandros
 Lattas</a>4,
 
 
 <a href="https://moschoglou.com/" target="_blank" rel="noopener noreferrer">Stylianos
 Moschoglou</a>4,
 
 
 <a href="https://thabobeeler.com/" target="_blank" rel="noopener noreferrer">Thabo
 Beeler</a>4,
 
 
 <a href="https://people.mpi-inf.mpg.de/~theobalt/" target="_blank" rel="noopener noreferrer">Christian Theobalt</a>1,5
 
</div>

<div>
 1Max Planck Institute for Informatics, Saarland Informatics Campus,
 2SUTD,
 3A*STAR,
 4Google,
 5Saarbrücken Research Center for
 Visual Computing, Interaction and Artificial Intelligence
</div>

[[Project Page]](https://vcai.mpi-inf.mpg.de/projects/PSIVG/) | [[Paper]](https://arxiv.org/abs/2603.06408) | [[Video]](https://www.youtube.com/watch?v=AqneAlYzEAs)

![](https://raw.githubusercontent.com/MarkHershey/PSIVG/master/assets/fig1.jpg)

## Usage

Please refer to the [instructions.md](instructions.md) for environment setup and pipeline execution.

_**Disclaimer**: This repository offers a reference implementation of the pipeline described in the paper. The code is intended for research purposes only, is not optimized for robustness or production environments, and may not be actively maintained._

## License

This project is released under the [Apache 2.0 License](LICENSE).

## BibTeX

```bibtex
@InProceedings{Foo_2026_CVPR,
    author    = {Foo, Lin Geng and Huang, Mark He and Lattas, Alexandros and Moschoglou, Stylianos and Beeler, Thabo and Theobalt, Christian},
    title     = {Physical Simulator In-the-Loop Video Generation},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2026},
    pages     = {4301-4311}
}
```

## Acknowledgments

This project is built upon invaluable open-source research projects: [ViPE](https://github.com/nv-tlabs/vipe), [PhysGen3D](https://github.com/by-luckk/PhysGen3D), [Taichi](https://github.com/taichi-dev/taichi), [Taichi Elements](https://github.com/taichi-dev/taichi_elements), [Mitsuba](https://github.com/mitsuba-renderer/mitsuba3), [GroundingDINO](https://github.com/IDEA-Research/GroundingDINO), [SAM](https://github.com/facebookresearch/sam2), [LaMa](https://github.com/advimman/lama), [InstantMesh](https://github.com/TencentARC/InstantMesh), [lang-segment-anything](https://github.com/luca-medeiros/lang-segment-anything), [Go-with-the-Flow](https://github.com/Eyeline-Labs/Go-with-the-Flow), [cogvideox-factory](https://github.com/RyannDaGreat/cogvideox-factory), [CogVideoX](https://github.com/zai-org/CogVideo), [HunyuanVideo](https://github.com/Tencent-Hunyuan/HunyuanVideo).

We also thank these research projects for sharing their code: [pisa-experiments](https://github.com/vision-x-nyu/pisa-experiments), [MotionClone](https://github.com/LPengYang/MotionClone), [SG-I2V](https://github.com/Kmcode1/SG-I2V), [ImageConductor](https://github.com/liyaowei-stu/ImageConductor), [DragAnything](https://github.com/showlab/DragAnything), [VBench](https://github.com/Vchitect/VBench).

PSIVG

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README