7 papers
Loss-Resilient Semantic Communication over Packet-Loss Networks at Extreme-Low Bandwidth
Shengshi Yao, Jincheng Dai, Sixian Wang +5
In extreme-low bandwidth network scenarios, generative semantic codecs have emerged as promising solutions to reduce bandwidth cost for visual communications. However, these learne…
GVC-RT: Towards Real-Time Generative Video Compression at Ultra-Low Bitrates
Tianjian Dang, Sixian Wang, Lei Luo +2
Recent generative video codecs (GVCs) have achieved impressive reconstruction fidelity at ultra-low bitrates (< 0.02 bits per pixel) by compressing the tokens from generative token…
Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priors
Yunuo Chen, Chuqin Zhou, Jiangchuan Li +5
We present a novel paradigm for ultra-low-bitrate image compression (ULB-IC) that exploits the ``temporal'' evolution in generative image compression. Specifically, we define an ex…
On the Nonasymptotic Bounds of Joint Source-Channel Coding with Hierarchical Sources
Shuo Shao, Chao Qi, Jincheng Dai +2
This paper establishes tractable bounds of joint source-channel coding with hierarchical sources in the finite blocklength regime. In this setting, both the indirect source and obs…
Secure Digital Semantic Communications: Fundamentals, Challenges, and Opportunities
Weixuan Chen, Qianqian Yang, Yuanyuan Jia +5
Semantic communication (SemCom) has emerged as a promising paradigm for future wireless networks by prioritizing task-relevant meaning over raw data delivery, thereby reducing comm…
Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Textures
Chuqin Zhou, Xiaoyue Ling, Yunuo Chen +3
While recent neural codecs achieve strong performance at low bitrates when optimized for perceptual quality, their effectiveness deteriorates significantly under ultra-low bitrate…