Abstract

In this paper, we present a new method to deal with specular highlights in correspondence search. The proposed method is essentially based on the specular-free two-band image that we introduce to deal with specular reflection. For given input images, specular-free two-band images are generated using simple pixel-wise computations in real-time. Specular-free two-band images are then used to compute per-pixel raw matching costs. By using the specular-free two-band images instead of input images, reliable raw matching costs that are independent of the specularities of image pixels are obtained. As a result, we can find correct correspondences even in the presence of specular highlights. Experimental results show that the proposed method successfully produces accurate disparity maps for stereo images with specular highlights.