Superpixel Based Depth Propagation for Semi-Automatic 2D-to-3D Video Conversion

Abstract

In this paper, we proposed a super pixel based depth map propagation algorithm for the application in 2D to 3D video conversion. The proposed algorithm employs four main processes to generate depth maps for all frames in video sequences. First, the depth map of the key frames in the input sequences are generated by manual work. Second, the frames in the input sequences are over-segmented by Simple Linear Iterative Clustering (SLIC) method. Third, each super pixel in the non-key frame is used to match the corresponding super pixel in the key frame. Finally, the depth value in every super pixel is assigned by the matching result. The experiments showed that the proposed algorithm works well and give good depth generation quality and high efficiency.