KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

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

UniUGG

★ 63 Open GitHub ↗

[ICLR 2026] UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

<h1>UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic
Encoding</h1>

<div>
 Yueming Xu1&ast;,
 Jiahui Zhang1&ast;,
 Ze Huang1&ast;,
 Yurui Chen1,
 Yanpeng Zhou2,
 Zhenyu Chen2,
 Yu-Jie Yuan2,
 Pengxiang Xia2,
 Guowei Huang2,
 Xinyue Cai2,
 Zhongang Qi2,
 Xingyue Quan2,
 Jianye Hao2,
 Hang Xu2,
 
 <a href="https://lzrobots.github.io/" target="_blank">Li Zhang</a>1&dagger;
</div>

<div>
 1Fudan University&emsp;
 2Huawei Noah’s Ark Lab&emsp;
</div>

<img src="docs/resources/teaser.png" width="100%"/>
Overview of our UniUGG, the first unified framework for spatial understanding and generation. (A) UniUGG supports spatial-level VQA and generates geometrically consistent 3D scenes. (B) Given a reference image, it can creatively generate 3D variations and describe them accurately. (C) UniUGG outperforms baselines in both spatial understanding and generation, with our specially tuned vision encoder excelling in downstream tasks.

</div>

## 🎞️ [Demo Video](https://fudan-zvg.github.io/UniUGG/assets/demo.mp4)

## 📚 Bibtex

If you find this project or dataset helpful, please consider citing our paper:

```bibtex
@article{xu2025uniugg,
    title={UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding},
    author={Xu, Yueming and Zhang, Jiahui and Huang, Ze and Chen, Yurui and Zhou, Yanpeng and Chen Zhenyu and Yuan, Yujie and Xia, Pengxiang and Huang, Guowei and Cai, Xinyue and Qi, Zhongang and Quan, Xingyue and Hao, Jianye and Xu, Hang and Zhang, Li},
    year={2025},
    journal={arXiv preprint arXiv:2508.11952},
}
```

## ✅ TODO
✔ Release vision encoder module\
✔ Encoder pretraining pipeline\
✔ Pretrained checkpoints

✘ Spatial-VAE module  
✘ Unified Understanding and Generation

## 🔄Pipeline Overview
<img src="docs/resources/overview.png" width="100%"/>

### 🧩 Vision encoder pretraining
The detailed implementation of the encoder is provided in:
👉 **[Encoder README](src/encoder/README.md)**

UniUGG

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README