Wasserstein Patch Prior for Image Superresolution
Johannes Hertrich, Antoine Houdard, Claudia Redenbach

TL;DR
This paper proposes a Wasserstein patch prior for image superresolution that leverages a reference image with similar patch distribution to improve reconstruction quality, demonstrated through 2D and 3D examples.
Contribution
It introduces a novel regularizer based on Wasserstein distance of patch distributions for superresolution, applicable to 2D and 3D images.
Findings
Effective in superresolution tasks with texture and material images
Improves reconstruction quality by matching patch distributions
Validated through numerical experiments in 2D and 3D
Abstract
In this paper, we introduce a Wasserstein patch prior for superresolution of two- and three-dimensional images. Here, we assume that we have given (additionally to the low resolution observation) a reference image which has a similar patch distribution as the ground truth of the reconstruction. This assumption is e.g. fulfilled when working with texture images or material data. Then, the proposed regularizer penalizes the -distance of the patch distribution of the reconstruction to the patch distribution of some reference image at different scales. We demonstrate the performance of the proposed regularizer by two- and three-dimensional numerical examples.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Image Processing Techniques · Image and Signal Denoising Methods · Sparse and Compressive Sensing Techniques
