SuperPatchMatch: An Algorithm for Robust Correspondences Using Superpixel Patches

DOI10.1109/TIP.2017.2708504MaRDI QIDQ4618983zbMATH OpenDBLPWikidataFDO

Authors Rémi Giraud, Vinh-Thong Ta, Aurélie Bugeau, Pierrick Coupé, Nicolas Papadakis

Publication date 5 February 2019

Published in IEEE Transactions on Image Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1903.07169

Mathematics Subject Classification ID

Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Abstract: 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.

Recommendations

• Fast marching based superpixels
• Structure-sensitive superpixels via geodesic distance
• Robust correspondence recognition for computer vision
• Fast marching based superpixels generation
• Robust Superpixel Tracking

Cited in

(2)

• Thin structures retrieval using anisotropic neighborhoods of superpixels: application to shape-from-focus
• SuperPatchMatch

Describes a project that uses

Uses Software

• TreeCANN
• SCALP

This page was built for publication: SuperPatchMatch: An Algorithm for Robust Correspondences Using Superpixel Patches

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4618983)