Learning to Generate Wasserstein Barycenters

by   Julien Lacombe, et al.

Optimal transport is a notoriously difficult problem to solve numerically, with current approaches often remaining intractable for very large scale applications such as those encountered in machine learning. Wasserstein barycenters – the problem of finding measures in-between given input measures in the optimal transport sense – is even more computationally demanding as it requires to solve an optimization problem involving optimal transport distances. By training a deep convolutional neural network, we improve by a factor of 60 the computational speed of Wasserstein barycenters over the fastest state-of-the-art approach on the GPU, resulting in milliseconds computational times on 512×512 regular grids. We show that our network, trained on Wasserstein barycenters of pairs of measures, generalizes well to the problem of finding Wasserstein barycenters of more than two measures. We demonstrate the efficiency of our approach for computing barycenters of sketches and transferring colors between multiple images.



There are no comments yet.


page 8

page 10

page 14

page 17


The Monge-Kantorovich Optimal Transport Distance for Image Comparison

This paper focuses on the Monge-Kantorovich formulation of the optimal t...

Optimal Transport Relaxations with Application to Wasserstein GANs

We propose a family of relaxations of the optimal transport problem whic...

Interior-point Methods Strike Back: Solving the Wasserstein Barycenter Problem

Computing the Wasserstein barycenter of a set of probability measures un...

Local Bures-Wasserstein Transport: A Practical and Fast Mapping Approximation

Optimal transport (OT)-based methods have a wide range of applications a...

Computing Kantorovich-Wasserstein Distances on d-dimensional histograms using (d+1)-partite graphs

This paper presents a novel method to compute the exact Kantorovich-Wass...

Differential Geometric Retrieval of Deep Features

Comparing images to recommend items from an image-inventory is a subject...

Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark

Despite the recent popularity of neural network-based solvers for optima...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.