DASC: Dense Adaptive Self-Correlation Descriptor for Multi-Modal and Multi-Spectral Correspondence

Seungryong Kim, Dongbo Min, Bumsub Ham, Seungchul Ryu, Minh N. Do, Kwanghoon Sohn; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 2103-2112

Abstract


Establishing dense visual correspondence between multiple images is a fundamental task in many applications of computer vision and computational photography. Classical approaches, which aim to estimate dense stereo and optical flow fields for images adjacent in viewpoint or in time, have been dramatically advanced in recent studies. However, finding reliable visual correspondence in multi-modal or multi-spectral images still remains unsolved. In this paper, we propose a new dense matching descriptor, called dense adaptive self-correlation (DASC), to effectively address this kind of matching scenarios. Based on the observation that a self-similarity existing within images is less sensitive to modality variations, we define a novel descriptor with a series of an adaptive self-correlation similarity for patches within a local support window. To further improve the matching quality and runtime efficiency, we propose a patch-wise receptive field pooling, in which a sampling pattern is optimized with a discriminative learning. Moreover, the computational redundancy that arises when computing densely sampled descriptor over an entire image is dramatically reduced by applying fast edge-aware filtering. Experiments demonstrate the outstanding performance of the DASC descriptor in many cases of multi-modal and multi-spectral correspondence.

Related Material


[pdf]
[bibtex]
@InProceedings{Kim_2015_CVPR,
author = {Kim, Seungryong and Min, Dongbo and Ham, Bumsub and Ryu, Seungchul and Do, Minh N. and Sohn, Kwanghoon},
title = {DASC: Dense Adaptive Self-Correlation Descriptor for Multi-Modal and Multi-Spectral Correspondence},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}