Recent Advances of End-to-End Video Coding Technologies for AVS Standard Development

📅 2026-01-31
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the challenge of balancing compression efficiency and computational complexity in practical deployments of intelligent video coding. We propose an end-to-end low-complexity coding framework tailored to standardized common test conditions, integrated into the AVS-EEM platform. By leveraging a customized neural network architecture, efficient training strategies, and inference optimization techniques—all while strictly adhering to conventional coding common test conditions—the proposed approach substantially reduces computational overhead. After more than two years of iterative development, the latest model significantly outperforms the AVS3 reference software in compression performance under identical test conditions, marking a critical step toward the standardization and practical adoption of end-to-end intelligent video coding.

Technology Category

Application Category

📝 Abstract
Video coding standards are essential to enable the interoperability and widespread adoption of efficient video compression technologies. In pursuit of greater video compression efficiency, the AVS video coding working group launched the standardization exploration of end-to-end intelligent video coding, establishing the AVS End-to-End Intelligent Video Coding Exploration Model (AVS-EEM) project. A core design principle of AVS-EEM is its focus on practical deployment, featuring inherently low computational complexity and requiring strict adherence to the common test conditions of conventional video coding. This paper details the development history of AVS-EEM and provides a systematic introduction to its key technical framework, covering model architectures, training strategies, and inference optimizations. These innovations have collectively driven the project's rapid performance evolution, enabling continuous and significant gains under strict complexity constraints. Through over two years of iterative refinement and collaborative effort, the coding performance of AVS-EEM has seen substantial improvement. Experimental results demonstrate that its latest model achieves superior compression efficiency compared to the conventional AVS3 reference software, marking a significant step toward a deployable intelligent video coding standard.
Problem

Research questions and friction points this paper is trying to address.

end-to-end video coding
intelligent video coding
compression efficiency
computational complexity
AVS standard
Innovation

Methods, ideas, or system contributions that make the work stand out.

end-to-end video coding
intelligent video compression
low computational complexity
AVS standard
model optimization
🔎 Similar Papers
No similar papers found.
Xihua Sheng
Xihua Sheng
University of Science and Technology of China->City University of Hong Kong
Video codingImage codingPoint Cloud coding
X
Xiongzhuang Liang
MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei 230093, China
Chuanbo Tang
Chuanbo Tang
University of Science and Technology of China
video compression, image compression
Z
Zhirui Zuo
MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei 230093, China
Yifan Bian
Yifan Bian
University of Science & Technology of China
Deep learningend-to-end based image/video compression
Y
Yutao Xie
MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei 230093, China
Zhuoyuan Li
Zhuoyuan Li
University of Science and Technology of China (USTC)
Video CodingInter/Intra PredictionIn-Loop FilteringLearned Compression
Yuqi Li
Yuqi Li
University of Science and Technology of China
Image Compression
H
Hui Xiang
MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei 230093, China
Li Li
Li Li
University of Science and Technology of China
video compressionpoint cloud compressionvolumetric data compression
Dong Liu
Dong Liu
University of Science and Technology of China
Electrical impedance tomographyshape modelingtopology optimizationshape reconstructionlevel set method