用快速傅里叶与切片距离加速异构图像对齐，效率达O(L² log L)
Fast rigid alignment of heterogeneous images in sliced Wasserstein distance
- 结合快速傅里叶与切片2-Wasserstein距离实现高效对齐
- 在O(L² log L)复杂度下完成L×L图像对齐，支持旋转变形鲁棒性
- 适合需要快速、稳健图像配准的计算机视觉任务
计算机视觉中许多应用依赖于相似但非完全相同的图像对齐。本文提出一种基于最优传输的快速算法，结合快速傅里叶方法的速度与切片概率度量的鲁棒性，可在O(L² log L)操作内高效计算两个L×L图像间的切片2-Wasserstein距离，实现对齐。实验表明该方法对图像平移、旋转和形变具有鲁棒性。
原文摘要 · Abstract (English)
Many applications of computer vision rely on the alignment of similar but non-identical images. We present a fast algorithm for aligning heterogeneous images based on optimal transport. Our approach combines the speed of fast Fourier methods with the robustness of sliced probability metrics and allows us to efficiently compute the alignment between two $L \times L$ images using the sliced 2-Wasserstein distance in $O(L^2 \log L)$ operations. We show that our method is robust to translations, rotations and deformations in the images.
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。