不用传统成本体积，仅靠图像扭曲实现更高效精准的立体匹配。
WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching
- 用图像扭曲替代成本体积构建匹配特征。
- 在ETH3D、Middlebury、KITTI上均排名第一，零样本误差降81%。
- 速度比同类方法快1.8到6.7倍，适合实时立体视觉应用。
我们提出WAFT-Stereo，一种基于图像扭曲的简单而高效的立体匹配方法。该方法表明，许多先进方法中常用的成本体积并非性能关键，可被更高效的扭曲机制替代。WAFT-Stereo在ETH3D（BP-0.5）、Middlebury（RMSE）和KITTI（所有指标）上均取得最佳表现，使ETH3D的零样本误差降低81%，同时比现有方法快1.8至6.7倍。代码与模型权重已公开于https://github.com/princeton-vl/WAFT-Stereo。
原文摘要 · Abstract (English)
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 (BP-0.5), Middlebury (RMSE), and KITTI (all metrics), reducing the zero-shot error by 81% on ETH3D, while being 1.8-6.7x faster than competitive methods. Code and model weights are available at https://github.com/princeton-vl/WAFT-Stereo.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。