6 papers · 1 filter
A Synonymous Variational Perspective on the Rate-Distortion-Perception Tradeoff
Zijian Liang, Kai Niu, Changshuo Wang +2
The fundamental limit of natural signal compression has traditionally been characterized by classical rate-distortion (RD) theory through the tradeoff between coding rate and recon…
A Theoretical Framework for Rate-Distortion Limits in Learned Image Compression
Changshuo Wang, Zijian Liang, Kai Niu +1
We present a novel systematic theoretical framework to analyze the rate-distortion (R-D) limits of learned image compression. While recent neural codecs have achieved remarkable em…
Way to Build Native AI-driven 6G Air Interface: Principles, Roadmap, and Outlook
Ping Zhang, Kai Niu, Yiming Liu +8
Artificial intelligence (AI) is expected to serve as a foundational capability across the entire lifecycle of 6G networks, spanning design, deployment, and operation. This article…
Neural Coding Is Not Always Semantic: Toward the Standardized Coding Workflow in Semantic Communications
Hai-Long Qin, Jincheng Dai, Sixian Wang +5
Semantic communication, leveraging advanced deep learning techniques, emerges as a new paradigm that meets the requirements of next-generation wireless networks. However, current s…
Synonymous Variational Inference for Perceptual Image Compression
Zijian Liang, Kai Niu, Changshuo Wang +2
Recent contributions of semantic information theory reveal the set-element relationship between semantic and syntactic information, represented as synonymous relationships. In this…
Deep Generative Modeling Reshapes Compression and Transmission: From Efficiency to Resiliency
Jincheng Dai, Xiaoqi Qin, Sixian Wang +3
Information theory and machine learning are inextricably linked and have even been referred to as "two sides of the same coin". One particularly elegant connection is the essential…