CVGRIRAug 7, 2020

SimPatch: A Nearest Neighbor Similarity Match between Image Patches

arXiv:2008.03085v1
AI Analysis

This work addresses a fundamental building block in image processing tasks, but it appears incremental as it focuses on patch size and feature extraction without introducing a new paradigm.

The paper tackles the problem of measuring similarity between image patches by using large patches and different feature extraction mechanisms to form feature matrices, and it demonstrates results using two nearest neighbor algorithms for finding nearest neighbor patches.

Measuring the similarity between patches in images is a fundamental building block in various tasks. Naturally, the patch-size has a major impact on the matching quality, and on the consequent application performance. We try to use large patches instead of relatively small patches so that each patch contains more information. We use different feature extraction mechanisms to extract the features of each individual image patches which forms a feature matrix and find out the nearest neighbor patches in the image. The nearest patches are calculated using two different nearest neighbor algorithms in this paper for a query patch for a given image and the results have been demonstrated in this paper.

Foundations

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

Your Notes