Fast rigid alignment of heterogeneous images in sliced Wasserstein distance

Abstract

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.

References in corpus (4)

• Galaxy Zoo : Morphologies derived from visual inspection of galaxies from the Sloan Digital Sky Survey
• The Radon cumulative distribution transform and its application to image classification
• Factorization of the translation kernel for fast rigid image alignment
• Radial-recombination for rigid rotational alignment of images and volumes