Convolutional wasserstein distances - Archive ouverte HAL Access content directly
Journal Articles ACM Transactions on Graphics Year : 2015

Convolutional wasserstein distances

Abstract

This paper introduces a new class of algorithms for optimization problems involving optimal transportation over geometric domains. Our main contribution is to show that optimal transportation can be made tractable over large domains used in graphics, such as images and triangle meshes, improving performance by orders of magnitude compared to previous work. To this end, we approximate optimal transportation distances using entropic regularization. The result- ing objective contains a geodesic distance-based kernel that can be approximated with the heat kernel. This approach leads to simple iterative numerical schemes with linear convergence, in which each iteration only requires Gaussian convolution or the solution of a sparse, pre-factored linear system. We demonstrate the versatility and efficiency of our method on tasks including reflectance interpolation, color transfer, and geometry processing.
Fichier principal
Vignette du fichier
2015-SIGGRAPH-convolutional-ot.pdf (2.37 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01188953 , version 1 (01-09-2015)

Identifiers

Cite

Justin Solomon, Fernando de Goes, Gabriel Peyré, Marco Cuturi, Adrian Butscher, et al.. Convolutional wasserstein distances. ACM Transactions on Graphics, 2015, 34 (4), pp.66:1-66:11. ⟨10.1145/2766963⟩. ⟨hal-01188953⟩
2282 View
3600 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More