Stereo Matching with Confidence-Region Decomposition and Processing

Abstract

We introduce a new stereo matching algorithm that estimates disparities in high-confidence and low-confidence regions separately. Stereo matching algorithm play an important role in 3D rendering since 3D structures and virtual scenes can be built by disparity map. A complementary tree structure is adopted to identify the high-confidence region and estimate its disparity map using dynamic programming. Then, a disparity fitting algorithm restores the disparities in low-confidence regions using the color and disparity information of high-confidence regions through a global optimization technique. The proposed stereo matching algorithm enhances disparity values in both occlusion and difficult-to-estimate areas (e.g., thin objects), to yield a high quality disparity map.