CVNASep 27, 2021

Wasserstein Patch Prior for Image Superresolution

arXiv:2109.12880v224 citations
Originality Incremental advance
AI Analysis

This method addresses superresolution for texture or material images where a reference with similar patch distributions is available, representing an incremental improvement.

The paper tackles the problem of image superresolution by introducing a Wasserstein patch prior that penalizes the W2-distance between patch distributions of the reconstruction and a reference image at multiple scales, demonstrating performance through 2D and 3D numerical examples.

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 $W_2$-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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes