Discovering Texture Regularity as a Higher-Order Correspondence Problem
Abstract
Understanding texture regularity in real images is a challenging computer vision task. We propose a higher-order feature matching algorithm to discover the lattices of near-regular textures in real images. The underlying lattice of a near-regular texture identifies all of the texels as well as the global topology among the texels. A key contribution of this paper is to formulate lattice-finding as a correspondence problem. The algorithm finds a plausible lattice by iteratively proposing texels and assigning neighbors between the texels. Our matching algorithm seeks assignments that maximize both pair-wise visual similarity and higher-order geometric consistency. We approximate the optimal assignment using a recently developed spectral method. We successfully discover the lattices of a diverse set of unsegmented, real-world textures with significant geometric warping and large appearance variation among texels.
BibTeX
@conference{Hays-2006-9442,author = {James H. Hays and Marius Leordeanu and Alexei A. Efros and Yanxi Liu},
title = {Discovering Texture Regularity as a Higher-Order Correspondence Problem},
booktitle = {Proceedings of (ECCV) European Conference on Computer Vision},
year = {2006},
month = {May},
pages = {522 - 535},
}