Wide-baseline stereo matching using ASIFT and POC

This paper proposes an accurate, dense and robust wide-baseline stereo correspondence matching method combining ASIFT (Affine-SIFT) and POC (Phase-Only Correlation). ASIFT-based matching is robust against perspective deformation of the stereo images, while the corresponding points are sparse. POC-based matching can find dense correspondence, while the corresponding points are not reliable in the case of the wide-baseline stereo. The complementary use of ASIFT and POC makes it possible to find accurate and dense stereo correspondence regardless of the length of camera baseline. Through a set of experiments, we demonstrate that the proposed method exhibits efficient performance compared with the conventional methods. We also apply the proposed method to 3D reconstruction from multi-view images.