Reinforcement Learning for HEVC/H.265 Frame-level Bit Allocation

Lian Ching Chen, Jun Hao Hu, Wen-Hsiao Peng

研究成果: Conference contribution同行評審

摘要

Frame-level bit allocation is crucial to video rate control. The problem is often cast as minimizing the distortions of a group of video frames subjective to a rate constraint. When these video frames are related through inter-frame prediction, the bit allocation for different frames exhibits dependency. To address such dependency, this paper introduces reinforcement learning. We first consider frame-level texture complexity and bit balance as a state signal, define the bit allocation for each frame as an action, and compute the negative frame-level distortion as an immediate reward signal. We then train a neural network to be our agent, which observes the state to allocate bits to each frame in order to maximize cumulative reward. As compared to the rate control scheme in HM-16.15, our method shows better PSNR performance while having smaller bit rate fluctuations.

原文English
主出版物標題2018 IEEE 23rd International Conference on Digital Signal Processing, DSP 2018
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781538668115
DOIs
出版狀態Published - 31 1月 2019
事件23rd IEEE International Conference on Digital Signal Processing, DSP 2018 - Shanghai, China
持續時間: 19 11月 201821 11月 2018

出版系列

名字International Conference on Digital Signal Processing, DSP
2018-November

Conference

Conference23rd IEEE International Conference on Digital Signal Processing, DSP 2018
國家/地區China
城市Shanghai
期間19/11/1821/11/18

指紋

深入研究「Reinforcement Learning for HEVC/H.265 Frame-level Bit Allocation」主題。共同形成了獨特的指紋。

引用此