README.md

---
license: apache-2.0
pipeline_tag: image-to-3d
---

<div align="center">

# [CVPR 2026 (Highlight)] Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images

Xiangyu Sun*, Haoyi Jiang*, Liu Liu, Seungtae Nam, Gyeongjin Kang, Xinjie Wang,</br>
Wei Sui, Zhizhong Su, Wenyu Liu, Xinggang Wang, Eunbyung Park

[![Project page](https://img.shields.io/badge/project%20page-Uni3R-blue)](https://horizonrobotics.github.io/robot_lab/uni3R)
[![ArXiv](https://img.shields.io/badge/arXiv-2508.03643-red?logo=arXiv&logoColor=red)](https://arxiv.org/abs/2508.03643)
[![Repository](https://img.shields.io/badge/Repository-GitHub-green?logo=github)](https://github.com/HorizonRobotics/Uni3R)

</div>



## Citation

```bibTeX
@misc{sun2026uni3runified3dreconstruction,
      title={Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images}, 
      author={Xiangyu Sun and Haoyi Jiang and Liu Liu and Seungtae Nam and Gyeongjin Kang and Xinjie Wang and Wei Sui and Zhizhong Su and Wenyu Liu and Xinggang Wang and Eunbyung Park},
      year={2026},
      eprint={2508.03643},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2508.03643}, 
}
```