Update model card with paper link, GitHub repo, and pipeline tag

Hi! I'm Niels from the Hugging Face community science team. I've updated the model card to include:
- Metadata for the `pipeline_tag` (enabling the "Depth Estimation" category on the Hub).
- Links to the paper and the official GitHub repository.
- A brief description of the model and its performance on benchmarks.
- Citation information for researchers.

README.md

@@ -1,3 +1,29 @@
----
-license: bsd-3-clause
----
+---
+license: bsd-3-clause
+pipeline_tag: depth-estimation
+---
+
+# WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching
+
+WAFT-Stereo is a simple and effective warping-based method for stereo matching. It demonstrates that cost volumes, a common design used in many leading methods, are not necessary for strong performance and can be replaced by warping with improved efficiency. 
+
+WAFT-Stereo ranks first on ETH3D, KITTI and Middlebury public benchmarks, reducing the zero-shot error by 81% on ETH3D benchmark, while being 1.8-6.7x faster than competitive methods.
+
+- **Paper:** [WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching](https://huggingface.co/papers/2603.24836)
+- **Repository:** [https://github.com/princeton-vl/WAFT-Stereo](https://github.com/princeton-vl/WAFT-Stereo)
+
+## Citation
+
+If you find WAFT-Stereo useful for your work, please consider citing the paper:
+
+```bibtex
+@misc{wang2026waftstereowarpingalonefieldtransforms,
+      title={WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching}, 
+      author={Yihan Wang and Jia Deng},
+      year={2026},
+      eprint={2603.24836},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2603.24836}, 
+}
+```