Title :
Joint Spectral Correspondence for Disparate Image Matching
Author :
Bansal, Mayank ; Daniilidis, Kostas
Author_Institution :
GRASP Lab., Univ. of Pennsylvania, Philadelphia, PA, USA
Abstract :
We address the problem of matching images with disparate appearance arising from factors like dramatic illumination (day vs. night), age (historic vs. new) and rendering style differences. The lack of local intensity or gradient patterns in these images makes the application of pixel-level descriptors like SIFT infeasible. We propose a novel formulation for detecting and matching persistent features between such images by analyzing the eigen-spectrum of the joint image graph constructed from all the pixels in the two images. We show experimental results of our approach on a public dataset of challenging image pairs and demonstrate significant performance improvements over state-of-the-art.
Keywords :
gradient methods; graph theory; image matching; SIFT; disparate appearance; disparate image matching; dramatic illumination; eigen-spectrum; gradient patterns; image pixel; joint image graph; joint spectral correspondence; local intensity; pixel-level descriptors; Detectors; Feature extraction; Image segmentation; Joints; Laplace equations; Lighting; Vectors; Eigen; Spectral; features; image graph; matching;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on
Conference_Location :
Portland, OR
DOI :
10.1109/CVPR.2013.361