Update README.md

README.md

@@ -6,6 +6,49 @@ tags:
 - pytorch_model_hub_mixin
 ---
 
-This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
-- Library: https://github.com/jiah-cloud/Align3R
-- Docs: [More Information Needed]
+
+<a href='https://arxiv.org/abs/2412.03079'><img src='https://img.shields.io/badge/arXiv-2412.03079-b31b1b.svg'></a> &nbsp;
+<a href='https://igl-hkust.github.io/Align3R.github.io/'><img src='https://img.shields.io/badge/Project-Page-Green'></a> &nbsp;
+<a href='https://github.com/jiah-cloud/Align3R'><img src='https://img.shields.io/badge/Github-Repo-blue'></a> &nbsp;
+
+
+[**Align3R: Aligned Monocular Depth Estimation for Dynamic Videos**](https://arxiv.org/abs/2412.03079)
+[*Jiahao Lu*\*](https://github.com/jiah-cloud),
+[*Tianyu Huang*\*](https://scholar.google.com/citations?view_op=list_works&hl=en&user=nhbSplwAAAAJ),
+[*Peng Li*](https://scholar.google.com/citations?user=8eTLCkwAAAAJ&hl=zh-CN),
+[*Zhiyang Dou*](https://frank-zy-dou.github.io/),
+[*Cheng Lin*](https://clinplayer.github.io/),
+[*Zhiming Cui*](),
+[*Zhen Dong*](https://dongzhenwhu.github.io/index.html),
+[*Sai-Kit Yeung*](https://saikit.org/index.html),
+[*Wenping Wang*](https://scholar.google.com/citations?user=28shvv0AAAAJ&hl=en),
+[*Yuan Liu*](https://liuyuan-pal.github.io/)
+Arxiv, 2024. 
+
+**Align3R** estimates temporally consistent video depth, dynamic point clouds, and camera poses from monocular videos.
+<video controls>
+  <source src="https://igl-hkust.github.io/Align3R.github.io/static/video/converted/output_video.mp4" type="video/mp4">
+</video>
+
+
+
+```bibtex
+@article{lu2024align3r,
+  title={Align3R: Aligned Monocular Depth Estimation for Dynamic Videos},Jiahao Lu, Tianyu Huang, Peng Li, Zhiyang Dou, Cheng Lin, Zhiming Cui, Zhen Dong, Sai-Kit Yeung, Wenping Wang, Yuan Liu
+  author={Lu, Jiahao and Huang, Tianyu and Li, Peng and Dou, Zhiyang and Lin, Cheng and Cui, Zhiming and Dong, Zhen and Yeung, Sai-Kit and Wang, Wenping and Liu,Yuan},
+  journal={arXiv preprint arXiv:2412.03079},
+  year={2024}
+}
+```
+
+### How to use
+
+First, [install Align3R](https://github.com/jiah-cloud/Align3R).
+To load the model:
+
+```python
+from dust3r.model import AsymmetricCroCo3DStereo
+import torch
+model = AsymmetricCroCo3DStereo.from_pretrained("cyun9286/Align3R_DepthAnythingV2_ViTLarge_BaseDecoder_512_dpt")
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)