Abstract
WAFT-Stereo achieves state-of-the-art stereo matching performance by replacing cost volumes with warping techniques, demonstrating superior efficiency and accuracy on major benchmarks.
We introduce WAFT-Stereo, a simple and effective warping-based method for stereo matching. WAFT-Stereo 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. Code and model weights are available at https://github.com/princeton-vl/WAFT-Stereo.
Community
New efficient state-of-the-art algorithm for rectified stereo:
Best-performing model:
#1 on ETH3D, Middlebury, and KITTI,
1.8-6.7x faster than competitive methods,
81% zero-shot error reduction.
Fastest model:
21FPS on qHD input,
up to 80% zero-shot error reduction.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Prompts (2026)
- Pip-Stereo: Progressive Iterations Pruner for Iterative Optimization based Stereo Matching (2026)
- StereoAdapter-2: Globally Structure-Consistent Underwater Stereo Depth Estimation (2026)
- MegaFlow: Zero-Shot Large Displacement Optical Flow (2026)
- Reference-Free Omnidirectional Stereo Matching via Multi-View Consistency Maximization (2026)
- Diachronic Stereo Matching for Multi-Date Satellite Imagery (2026)
- Deep S2P: Integrating Learning Based Stereo Matching Into the Satellite Stereo Pipeline (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2603.24836 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 1
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper