Joint frame-level and CTU-level rate control based on constant perceptual quality

For a given network bandwidth, optimizing the rate control to achieve the best compression performance is essential in video communication and storage. Besides the enhancement of the overall coding efficiency, the rate control algorithm for constant perceptual quality video coding is also a significant research topic in video coding. However, most existing constant perceptual quality rate control algorithms either emphasize on the frame level or the CTU level, which have not considered the local and global perceptual quality sufficiently. Therefore, this paper presents an improved joint frame-level and CTU-level constant perceptual quality rate control algorithm framework to further improve the quality consistence and compression performance. Firstly, we propose a frame-level constant perceptual quality rate control method based on just noticeable difference (JND) and game theory model. The method aims to effectively control the perceptual quality by optimizing the current frame-level Lagrange multiplier in the GOP (Group of Pictures). Secondly, taking into account the JND-based CTU-level spatial and temporal masking effects, we propose a joint intra-frame and inter-frame CTU-level perceptual rate control method. The method utilizes the frame-level Lagrange multiplier to generate the optimal perceptual coding performance for each CTU. Finally, by integrating the two levels of optimization, we develop an innovative constant perceptual quality rate control algorithm to efficiently balance the perceptual quality and rate control demands of video coding. Experiments demonstrate that the constant perceptual quality rate control algorithm proposed in this paper can achieve remarkable improvements in subjective and objective rate-distortion optimization performance, as well as quality constancy performance while ensuring the enhancement of rate control precision.