SuperPatchMatch: an Algorithm for Robust Correspondences using Superpixel Patches

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Giraud, Rémi, Ta, Vinh-Thong, Bugeau, Aurélie, Coupé, Pierrick, Papadakis, Nicolas
Format: Preprint
Published: 2019
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918147519414272
author Giraud, Rémi
Ta, Vinh-Thong
Bugeau, Aurélie
Coupé, Pierrick
Papadakis, Nicolas
author_facet Giraud, Rémi
Ta, Vinh-Thong
Bugeau, Aurélie
Coupé, Pierrick
Papadakis, Nicolas
contents Superpixels have become very popular in many computer vision applications. Nevertheless, they remain underexploited since the superpixel decomposition may produce irregular and non stable segmentation results due to the dependency to the image content. In this paper, we first introduce a novel structure, a superpixel-based patch, called SuperPatch. The proposed structure, based on superpixel neighborhood, leads to a robust descriptor since spatial information is naturally included. The generalization of the PatchMatch method to SuperPatches, named SuperPatchMatch, is introduced. Finally, we propose a framework to perform fast segmentation and labeling from an image database, and demonstrate the potential of our approach since we outperform, in terms of computational cost and accuracy, the results of state-of-the-art methods on both face labeling and medical image segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_1903_07169
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle SuperPatchMatch: an Algorithm for Robust Correspondences using Superpixel Patches
Giraud, Rémi
Ta, Vinh-Thong
Bugeau, Aurélie
Coupé, Pierrick
Papadakis, Nicolas
Computer Vision and Pattern Recognition
Superpixels have become very popular in many computer vision applications. Nevertheless, they remain underexploited since the superpixel decomposition may produce irregular and non stable segmentation results due to the dependency to the image content. In this paper, we first introduce a novel structure, a superpixel-based patch, called SuperPatch. The proposed structure, based on superpixel neighborhood, leads to a robust descriptor since spatial information is naturally included. The generalization of the PatchMatch method to SuperPatches, named SuperPatchMatch, is introduced. Finally, we propose a framework to perform fast segmentation and labeling from an image database, and demonstrate the potential of our approach since we outperform, in terms of computational cost and accuracy, the results of state-of-the-art methods on both face labeling and medical image segmentation.
title SuperPatchMatch: an Algorithm for Robust Correspondences using Superpixel Patches
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/1903.07169