Rate Control Method Based on Deep Reinforcement Learning for Dynamic Video Sequences in HEVC

Zhou, Mingliang; Wei, Xuekai; Jia, Weijia; Fang, Bin

doi:10.1109/tmm.2020.2992968

Cited by 43 publications

(17 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[24], [25] proposed using CNN to predict the probability distribution of the intra prediction related syntax elements. Reinforcement learning has been introduced into the traditional rate control to allocate bitrate and estimate coding parameters in [26], [27]. In order to remove the compression artifacts, He et al [28] proposed to use one kind of reference prior -the partition information to guide the quality enhancement combined with the distorted frame.…”

Section: B Deep Learning Based Video Codingmentioning

confidence: 99%

“…The second category methods still follow the conventional block based hybrid video coding framework [19]. The deep neural network is integrated into the framework to improve the performance of particular module including inter prediction [20]- [22], transform [23], entropy coding [24], [25], rate control [26], [27], in-loop filtering/post processing [28]- [31] and intra prediction [32]- [38] The details of these deep learning based video coding methods are reviewed in Section. II-B.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Current Frame Priors Assisted Neural Network for Intra Prediction

et al. 2021

View full text Add to dashboard Cite

Intra prediction is the key technology to reduce spatial redundancy in the modern video coding standard. Recently, deep learning based methods that directly generate the intra prediction by neural network achieve superior performance than traditional directional based intra prediction. However, these methods lack the ability to handle complex blocks which contain mixed directional textures or recurrent patterns since they only use the neighboring reference samples of the current one. The other intermediate information denoted as reference priors in this paper generated during the coding process is not exploited. In this paper, a Current Frame Priors assisted Neural Network (CFPNN) is presented to improve the intra prediction efficiency. Specifically, we utilize the local contextual information provided by the neighboring multiple references as the primary inference source. In addition to the neighboring references, we additionally use the other two reference priors within the current frame -the predictor searched by intra block copy (IntraBC) and the corresponding residual component. The IntraBC predictor provides useful nonlocal information to help generate more accurate prediction for complex blocks together with neighboring local information. While the residual component contains unique information that reflects the characteristics of the block to some extent is utilized to reduce the noise contained in the reconstructed reference samples. Moreover, we investigate the best way to integrate the proposed method into the codec. Experimental results demonstrate that compared to HEVC, our proposed CFPNN achieves an average of 4.1% BD-rate reduction for the luma component under the All Intra configuration.

show abstract

Section: B Deep Learning Based Video Codingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Current Frame Priors Assisted Neural Network for Intra Prediction

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Frame-level bit allocation is one key issue in video rate control [1][2][3]. The task is to minimize the distortion of a group of pictures (GOP) under a rate constraint.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, deep reinforcement learning (RL) emerged as a promising technique for addressing dependent decision-making. Some early attempts apply RL to tackle constrained optimization problems in the video coding area [1][2][3][4][5]. Chung et al [4] utilized RL to determine the partition of coding tree units in HEVC/H.265.…”

Section: Introductionmentioning

confidence: 99%

“…The idea was extended by Chen et al [1] to frame-level bit allocation for inter-frame coding with hierarchical bi-prediction. Lately, Zhou et al [3] took this line of research one step further for combined intra-and inter-frame bit allocation, focusing particularly on low-delay coding scenarios. Instead of optimizing video quality for human perception, Shi et al [5] proposed RL-based intra-frame bit allocation for image detection, classification, and segmentation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Dual-Critic Reinforcement Learning Framework for Frame-level Bit Allocation in HEVC/H.265

Jin

Liang

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper introduces a dual-critic reinforcement learning (RL) framework to address the problem of frame-level bit allocation in HEVC/H.265. The objective is to minimize the distortion of a group of pictures (GOP) under a rate constraint. Previous RL-based methods tackle such a constrained optimization problem by maximizing a single reward function that often combines a distortion and a rate reward. However, the way how these rewards are combined is usually ad hoc and may not generalize well to various coding conditions and video sequences. To overcome this issue, we adapt the deep deterministic policy gradient (DDPG) reinforcement learning algorithm for use with two critics, with one learning to predict the distortion reward and the other the rate reward. In particular, the distortion critic works to update the agent when the rate constraint is satisfied. By contrast, the rate critic makes the rate constraint a priority when the agent goes over the bit budget. Experimental results on commonly used datasets show that our method outperforms the bit allocation scheme in x265 and the single-critic baseline by a significant margin in terms of rate-distortion performance while offering fairly precise rate control.

show abstract