Search papers, labs, and topics across Lattice.
WAFT-Stereo achieves state-of-the-art stereo matching by replacing cost volumes with a warping-based approach using Warping-Alone Field Transforms. This simplification significantly improves efficiency, achieving 1.8-6.7x speedups compared to existing methods. WAFT-Stereo achieves first place on ETH3D, KITTI, and Middlebury benchmarks, with an 81% reduction in zero-shot error on ETH3D.
Cost volumes might be overkill: WAFT-Stereo proves you can ditch them for a warping-based approach and still dominate stereo matching benchmarks with significantly improved efficiency.
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.
