Create README.md

README.md

@@ -1,3 +1,43 @@
----
-license: cc-by-sa-4.0
----
+---
+license: cc-by-nc-sa-4.0
+language:
+- en
+---
+<h1 align="center">🦄 UniCorrn: Unified Correspondence Transformer Across 2D and 3D <br> CVPR 2026</h1>
+
+<div align="center">
+
+[Prajnan Goswami<sup>1*</sup>](https://prajnancv.github.io),
+[Tianye Ding<sup>1*</sup>](https://jerrygcding.github.io/),
+[Feng Liu<sup>2</sup>](https://scholar.google.com/citations?&user=uiqXutMAAAAJ),
+[Huaizu Jiang<sup>1</sup>](https://jianghz.me/)\
+<sup>1</sup> [Visual Intelligence Lab, Northeastern University](https://github.com/neu-vi), <sup>2</sup> [Adobe Research](https://research.adobe.com)\
+<sup>*</sup> Equal Contribution
+
+<a href="https://arxiv.org/abs/2605.04044"><img src="https://img.shields.io/badge/arXiv-2605.04044-b31b1b" alt="arXiv"></a>
+<a href="https://neu-vi.github.io/UniCorrn/"><img src="https://img.shields.io/badge/Project_Page-green" alt="Project Page"></a>
+
+</div>
+
+
+## Overview
+
+UniCorrn is the first correspondence model with shared weights that unifies 2D-2D, 2D-3D, and 3D-3D geometric matching with an end-to-end transformer architecture.
+
+This model space contains the large-scale pretrained weights from stage1 and stage2 training.
+
+## Quick Start
+
+Check out our [Github Repo](https://github.com/neu-vi/UniCorrn).
+
+
+## Citation
+If you find this repository useful in your research, please consider giving a star ⭐ and a citation
+```bibtex
+@inproceddings{goswami2026unicorrn,
+  title={UniCorrn: Unified Correspondence Transformer Across 2D and 3D},
+  author={Goswami, Prajnan and Ding, Tianye and Liu, Feng and Jiang, Huaizu},
+  booktitle={CVPR},
+  year={2026}
+}
+```