Fast Intra Mode Decision for 3D-HEVC Depth Map Coding using Decision Trees

Abstract

This paper presents a fast intra mode decision for depth map coding on 3D-High Efficiency Video Coding (3D-HEVC) based on decision trees. The proposed solution uses data mining and machine learning to correlate the encoder context attributes and build a set of decision trees. Each decision tree defines if a depth map block must be or not be evaluated by the Depth Modeling Modes (DMMs), considering the encoding context. The decision trees were trained using data extracted from the 3D-HEVC Test Model (3D-HTM) under all-intra encoder configuration. The proposed solution was evaluated according to the Common Test Conditions (CTC), reducing 50.2% the execution time of the depth map coding, and impacting only 0.07% in the Bjontegaard Delta BitRate (BDBR) of the synthesized views.

Fast Algorithm for CU Size Decision Based on Ensemble Clustering for Intra Coding of VVC 3D Video Depth Map

“…Another study [21] proposes an intercomponent tool that uses links to save runtime through the joint encoding of quadtrees. A fast decision-making method based on decision trees for depth graph coding was proposed in [22]. The method uses data mining and machine learning to associate encoder contextual attributes and construct a set of decision trees.…”