Frame Level Quantization Control with Temporal Distortion Propagation Model for Video Coding

Abstract

In video coder, inter-frame prediction causes distortion propagation among temporally adjacent frames, which complicates frame level bit allocation and quantization control. Quantization parameter cascading (QPC) is generally employed to determine a sequence of quantization parameter for dependent rate distortion optimization (RDO). This paper proposes a general framework for temporal dependency analysis by lever-aging a distortion propagation model. The amount of distortion propagated from the temporally adjacent frames is measured by tree-style dependent analysis. Then, a trellis comprised of frame level quantization parameters of one GOP is constructed to achieve global optimization via branch-prune based dynamic programming. The simulation results verify that the frame level QPC algorithm with the proposed distortion model achieves up to 1.2dB—1.5dB PSNR improvement on average, with smaller temporal distortion fluctuation contributed by efficient bit allocation.