Lightweight Multiattention Recursive Residual CNN-Based In-Loop Filter Driven by Neuron Diversity

doi:10.1109/TCSVT.2023.3270729

	Lightweight Multiattention Recursive Residual CNN-Based In-Loop Filter Driven by Neuron Diversity
	Li, Mingxuan 1,2; Ji, Wen 1,3
	2023-11-01
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
ISSN	1051-8215
卷号	33 期号:11 页码:6996-7008
摘要	Many convolutional neural network (CNN)-based in-loop filters have been proposed to improve coding performance. However, considering the single perception scale, high parameter complexity, and the need to train multiple models for various quantization parameters (QPs), the performance and practicability of most existing methods are limited. Inspired by neuron diversity, this paper proposes a lightweight multiattention recursive residual CNN-based in-loop filter that can handle encoded frames with various QP values, frame types (FTs), and temporal layers (TLs) via a single model. First, multiscale features are learned in the neural network and fused with the proposed multidensity block (MDB) and multiscale fusion attention group (MFAG). Second, a recursive structure is adopted to improve the model depth while saving many parameters. The proposed auxiliary parameter fusion attention (APFA) and long-short-term skip connection (LSTSC) models integrate QPs, FTs and TLs into the model while accelerating training. Finally, we propose implementing LMA-RRCNN in parallel with the standard in-loop filter and select the optimal enhanced result in each patch. The experimental results on standard test sequences show that the proposed method achieves on average 13.70% and 11.87% BD rate savings under all-intra and random-access configurations, respectively, outperforming other state-of-the-art approaches.
关键词	Video coding in-loop filtering convolutional neural network deep learning high-efficiency video coding (HEVC)
DOI	10.1109/TCSVT.2023.3270729
收录类别	SCI
语种	英语
资助项目	Beijing Natural Science Foundation[L221004] ; National Key Research and Development Program of China[2022YFF0902403] ; National Key Research and Development Program of China[2022YFE0125400] ; National Natural Science Foundation of China[62072440]
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:001093434100054
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/38108
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Ji, Wen
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100190, Peoples R China 3.Peng Cheng Lab, Shenzhen 518055, Peoples R China
推荐引用方式 GB/T 7714	Li, Mingxuan,Ji, Wen. Lightweight Multiattention Recursive Residual CNN-Based In-Loop Filter Driven by Neuron Diversity[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2023,33(11):6996-7008.
APA	Li, Mingxuan,&Ji, Wen.(2023).Lightweight Multiattention Recursive Residual CNN-Based In-Loop Filter Driven by Neuron Diversity.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,33(11),6996-7008.
MLA	Li, Mingxuan,et al."Lightweight Multiattention Recursive Residual CNN-Based In-Loop Filter Driven by Neuron Diversity".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 33.11(2023):6996-7008.