用高分辨率变形替代代价体，提升光流精度与速度
WAFT: Warping-Alone Field Transforms for Optical Flow
- 以高分辨率图像变形代替传统代价体，简化网络结构
- 在Spring/Sintel/KITTI上均达最优，零样本泛化能力最强
- 速度快1.3至4.1倍，适合实时光流应用
我们提出Warping-Alone Field Transforms（WAFT），一种简单高效的光流方法。WAFT与RAFT类似，但用高分辨率变形替代代价体，在保持更高精度的同时降低内存消耗。这一设计挑战了构建代价体是高性能必要条件的传统认知。WAFT是一种轻量、灵活的元架构，具有极小归纳偏置且不依赖特定设计。相比现有方法，其在Spring、Sintel和KITTI基准上排名第一，且在KITTI上实现最佳零样本泛化性能，同时比具备竞争力准确率的方法快1.3至4.1倍（如比Flowformer++快1.3倍，比CCMR+快4.1倍）。代码与模型权重已公开于https://github.com/princeton-vl/WAFT。
原文摘要 · Abstract (English)
We introduce Warping-Alone Field Transforms (WAFT), a simple and effective method for optical flow. WAFT is similar to RAFT but replaces cost volume with high-resolution warping, achieving better accuracy with lower memory cost. This design challenges the conventional wisdom that constructing cost volumes is necessary for strong performance. WAFT is a simple and flexible meta-architecture with minimal inductive biases and reliance on custom designs. Compared with existing methods, WAFT ranks 1st on Spring, Sintel, and KITTI benchmarks, achieves the best zero-shot generalization on KITTI, while being 1.3-4.1x faster than existing methods that have competitive accuracy (e.g., 1.3x than Flowformer++, 4.1x than CCMR+). Code and model weights are available at \href{https://github.com/princeton-vl/WAFT}{https://github.com/princeton-vl/WAFT}.
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。