Different from the conventional calculative methods, a learning-based initial quantization parameter (LIQP) method is proposed in this paper to improve rate control of high efficiency video coding (H.265). First, the framework for initial quantization parameter (QP) learning is proposed, where a novel equivalent approach to build the benchmark labels is proposed using the single rate-distortion (R-D) pair in each initial QP testing. With the criterion of maximizing the prediction accuracy of initial QPs, features and parameters of the learning model are refined. Instead of the traditionally used target bits per pixel (bpp) for intraframe, the target bpp for all remaining frames is proposed to avoid the empirical setting on intracoding bits, and thus the related inaccuracy can be prevented. We clearly present the motivations of the proposed LIQP method, as well as the reasons for the extracted features and model parameters. The proposed LIQP method outperforms the latest HM-16.14 by achieving significant gains on R-D performance (-15.48% BD-BR and 0.782 dB BD-PSNR gains), quality smoothness (1.581 dB versus 2.598 dB), and more stable buffer occupancy control, with similar high bit rate accuracy (99.84% versus 99.87%), and can also work well for scene change cases.
Bibliographical noteThis work was supported in part by the Natural Science Foundation of China under Grant 61801303 and Grant 61672443, in part by Hong Kong RGC General Research Fund 9042489 under Grant CityU 11206317, in part by Hong Kong RGC General Research Fund 9042322 under Grant CityU 11200116, in part by Hong Kong ITF UICP under Grant 9440174, and in part by the startup project of Shenzhen University under Grant 2018069.
- initial QP
- machine learning
- rate control
- support vector regression (SVR)
- video coding