Bilayer Stereo Matching

This paper presents two novel approaches for stereo matching. First, a bitwise algorithm for stereo matching is proposed. It represents the disparity of each pixel as a binary number, treats each bit separately and determines them step by step, each step determines one bit of the disparities and involves only a single graph cut computation. It reduces the computation complexity to (9(log2 n). Second, bilayer stereo matching for scenes consisting of foreground and background is proposed. Disparity field of foreground and background layers are recovered independently, and the final disparity field is composed using the disparity field of two layers. Discontinuity between foreground and background can be preserved successfully by this schema. Experimental results show that the combination of bitwise algorithm and bilayer stereo matching can support realtime applications such as desktop-based 3D visual communication.