Inverse problems using regularized optimal transport for computer graphicsMS35

The geometry of optimal transport provides a useful way to compare and interpolate histograms. Recent work on entropic regularization makes optimal transport computationally affordable and easy to implement. This talk presents Wasserstein Barycentric Projection and Wasserstein Dictionary Learning as an optimization over parameters within the entropic optimal transport framework. I will show numerous applications in computer graphics, for processing colors, geometry, images and material reflectances.

This presentation is part of Minisymposium “MS35 - Optimal Transport and Patch based Methods for Color Image Editing
organized by: Nicolas Papadakis (CNRS, Institut de Mathématiques de Bordeaux) , Rabin Julien (CNRS, Normandie Univ.) .

Nicolas Bonneel (CNRS/LIRIS)