MemorySlices nielsr HF Staff commited on
Commit
dfcf8ac
·
1 Parent(s): b5de0bd

Update model card with paper link, GitHub repo, and pipeline tag (#1)

Browse files

- Update model card with paper link, GitHub repo, and pipeline tag (42c001f030e5726ea78f0bf56567a94b2db871a2)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +29 -3
README.md CHANGED
@@ -1,3 +1,29 @@
1
- ---
2
- license: bsd-3-clause
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bsd-3-clause
3
+ pipeline_tag: depth-estimation
4
+ ---
5
+
6
+ # WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching
7
+
8
+ 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.
9
+
10
+ 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.
11
+
12
+ - **Paper:** [WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching](https://huggingface.co/papers/2603.24836)
13
+ - **Repository:** [https://github.com/princeton-vl/WAFT-Stereo](https://github.com/princeton-vl/WAFT-Stereo)
14
+
15
+ ## Citation
16
+
17
+ If you find WAFT-Stereo useful for your work, please consider citing the paper:
18
+
19
+ ```bibtex
20
+ @misc{wang2026waftstereowarpingalonefieldtransforms,
21
+ title={WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching},
22
+ author={Yihan Wang and Jia Deng},
23
+ year={2026},
24
+ eprint={2603.24836},
25
+ archivePrefix={arXiv},
26
+ primaryClass={cs.CV},
27
+ url={https://arxiv.org/abs/2603.24836},
28
+ }
29
+ ```