Browsing by Author "Chung, Chia-Hua"

Now showing 1 - 2 of 2

HEVC/H.265 CODING UNIT SPLIT DECISION USING DEEP REINFORCEMENT LEARNING
(2017-01-01)
Chung, Chia-Hua
;
Peng, Wen-Hsiao
;
Hu, Jun-Hao
;
資訊工程學系
;
Department of Computer Science
The video coding community has long been seeking more effective rate-distortion optimization techniques than the widely adopted greedy approach. The difficulty arises when we need to predict how the coding mode decision made in one stage would affect subsequent decisions and thus the overall coding performance. Taking a data-driven approach, we introduce in this paper deep reinforcement learning (RL) as a mechanism for the coding unit (CU) split decision in HEVC/H.265. We propose to regard the luminance samples of a CU together with the quantization parameter as its state, the split decision as an action, and the reduction in rate distortion cost relative to keeping the current CU intact as the immediate reward. Based on the Q-learning algorithm, we learn a convolutional neural network to approximate the rate distortion cost reduction of each possible state-action pair. The proposed scheme performs compatibly with the current full rate-distortion optimization scheme in HM-16.15, incurring a 2,5% average BD-rate loss. While also performing similarly to a conventional scheme that treats the split decision as a binary classification problem, our scheme can additionally quantify the rate-distortion cost reduction, enabling more applications.
Reinforcement Learning for HEVC/H.265 Intra-Frame Rate Control
(2018-01-01)
Hu, Jun-Hao
;
Peng, Wen-Hsiao
;
Chung, Chia-Hua
;
資訊工程學系
;
Department of Computer Science
Reinforcement learning has proven effective for solving decision making problems. However, its application to modern video codecs has yet to be seen. This paper presents an early attempt to introduce reinforcement learning to HEVC/H.265 intra-frame rate control. The task is to determine a quantization parameter value for every coding tree unit in a frame, with the objective being to minimize the frame-level distortion subject to a rate constraint. We draw an analogy between the rate control problem and the reinforcement learning problem, by considering the texture complexity of coding tree units and bit balance as the environment state, the quantization parameter value as an action that an agent needs to take, and the negative distortion of the coding tree unit as an immediate reward. We train a neural network based on Q-learning to be our agent, which observes the state to evaluate the reward for each possible action. When trained on only limited sequences, the proposed model can already perform comparably with the rate control algorithm in HM-16.15.