Rate-distortion-complexity analysis for prediction unit modes in 3D-HEVC depth coding

3D-HEVC achieves significant compression efficiency thanks to the addition of several tools and features for multiview and 3D video content on top of those already available in HEVC. However, such gains come at the cost of large increases in the encoding computational complexity, which is a problem for computationally and battery-constrained devices. As the use of each tool or feature yields different compression efficiency, those that do not contribute significantly should be the first to be disabled in a complexity-constrained system with limited computational resources. Thus, this paper presents two major analyses on the use of Prediction Unit (PU) modes in 3D-HEVC: a preliminary, statistical study and a Rate-Distortion-Complexity (RDC) analysis. The first study observed the occurrence of asymmetric and rectangular PU modes in depth maps, while the RDC analysis evaluated the impact caused by the deactivation of the least used modes during the encoding of depth maps, based on the results found in the preliminary study. Experimental results have shown that a computational complexity reduction of 9% can be achieved with a negligible rate-distortion penalty (0.1%) if the least used modes are disabled.