A fast intra prediction algorithm for DMM mode in depth map coding

As the extension of High Efficiency Video Coding (HEVC) for 3D video coding, 3DHEVC achieves high efficiency for the compression of the multi-view videos plus depth (MVD) format. In order to ensure the performance of depth map coding, a new depth intra coding tool called Depth Modeling Mode (DMM) is introduced. However, the process of DMM significantly increases the computational complexity of depth map coding due to the blind traversal of all wedgelet partitions. In this paper, a fast intra prediction algorithm for DMM mode in depth map coding is proposed. In the first step, the unnecessary DMM mode is skipped by judging whether the best prediction mode in Rough Mode Decision (RMD) is DC mode. In the second step, the direction information represented by a permitted angle range is acquired based on the best prediction mode achieved in RMD. In the third step, a searching subset is obtained based on the direction information and the position information represented by the coordinates of the pixel with biggest depth value change in each boundary of PU. Then the patterns within the searching subset are tested by view synthesis optimization (VSO) to find the minimum distortion partition. Compared with the coarse-refinement algorithm, the proposed algorithm shows significant time saving with acceptable performance loss. © 2016 SERSC.