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 flflow fifields for images adjacent in viewpoint or in time, have been dramatically advanced in recent studies. However, fifinding reliable visual correspondence in multi-modal or multi-spectral images still remains unsolved. In this paper, we propose a novel 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 defifine the 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 effificiency, we propose a randomized receptive fifield 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 fifiltering. Experiments demonstrate the outstanding performance of the DASC descriptor in many cases of multi-modal and multi-spectral correspondence