Novel Stereo-Matching Method Utilizing Surface Normal Data

Abstract

Stereo matching has a critical disadvantage in that 3D data acquired with this method is not accurate because only intensity data from the image can be utilized. Optimization processes such as belief propagation and graph cuts increase the robustness and accuracy of the 3D data, but these require significant computational power. We propose a novel method of stereo matching that utilizes surface normal data derived from the photometric stereo technique. We obtain an improved depth map without requiring additional optimization.