Learning-based approach for visual quality enhancement on high efficiency video coding standard

Abstract

High Efficiency Video Coding (HEVC) has dramatically enhanced the coding efficiency compared to the previous video coding standard, H.264/AVC. However, the existing rate control updates its parameters according to a fixed initialization, which can cause error prediction of bit allocation to each coding tree unit (CTU) in frames. In this work, a learning-based mapping between rate control parameters and video contents is proposed to achieve an accurate target bit rate and good video quality. The proposed framework contains two main structural codings, including spatial and temporal coding. We initiate an effective learning-based particle swarm optimization for both spatial and temporal coding to determine the optimal parameters at the CTU level. For temporal coding at the picture level, we introduce semantic residual information into the parameter updating process to regulate the bit correctly on the actual picture. Experimental results indicate that the proposed algorithm is effective for HEVC and outperforms the state-of-the-art rate control in the HEVC reference software (HM-16.10) by 0.19 dB on average and up to 0.41 dB for low delay P coding structure.