mlsanityData to 14 Oct 2026

Fast rigid alignment of heterogeneous images in sliced Wasserstein distance

arXiv 2503.13756 ↗First posted 17 Mar 2025cs.CV cs.NA math.NAcited by 4

Not on the map. Why?

Abstract (arXiv)

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 × L images using the sliced 2-Wasserstein distance in O(L2 log L) operations. We show that our method is robust to translations, rotations and deformations in the images.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 15 of its 53 references that are in the map. First posted on arXiv 17 Mar 2025.

Builds on

15 of 53 references.

References · 15

  1. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  2. 2018Computational Optimal Transportcited by 780
  3. 2019Max-Sliced Wasserstein Distance and its use for GANscited by 119
  4. 2018Generative Modeling using the Sliced Wasserstein Distancecited by 108
  5. 2015Sliced Wasserstein Kernels for Probability Distributionscited by 65
  6. 2015The Radon cumulative distribution transform and its application to image classificationcited by 28
  7. 2019Earthmover-based manifold learning for analyzing molecular conformation spacescited by 8
  8. 2023Alignment of Density Maps in Wasserstein Distancecited by 8
  9. 2020Centering noisy images with application to cryo-EMcited by 7
  10. 2022Invariance encoding in sliced-Wasserstein space for image classification with limited training datacited by 7
  11. 2022AlignOT: An optimal transport based algorithm for fast 3D alignment with applications to cryogenic electron microscopy density mapscited by 7
  12. 2020Wasserstein K-Means for Clustering Tomographic Projectionscited by 6
3 more
  1. 2022Nonequispaced Fast Fourier Transform Boost for the Sinkhorn Algorithmcited by 4
  2. 2022Ab-initio Contrast Estimation and Denoising of Cryo-EM Imagescited by 2
  3. 2023The Radon Signed Cumulative Distribution Transform and its applications in classification of Signed Imagescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Quantifying the noise sensitivity of the Wasserstein metric for imagescited by 0
  2. 2025Generalizations of the Normalized Radon Cumulative Distribution Transform for Limited Data Recognitioncited by 0
  3. 2026Application and Evaluation of the Common Circles Methodcited by 0
  4. 2026On the stability of scale-space metricscited by 0