用极小嵌入量实现高速高质图像传输，抗噪能力强。
Efficient and Robust Semantic Image Communication via Stable Cascade
- 用稳定级联思想压缩图像为0.29%大小的潜在嵌入进行传输
- 在噪声信道下重建质量超越3个基准方法，1024×1024图像快16倍
- 适合对速度与鲁棒性要求高的图像通信场景
基于扩散模型（DM）的语义图像通信（SIC）系统面临推理速度慢、生成随机性强等问题，影响其可靠性与实用性。为此，我们提出一种受Stable Cascade启发的新SIC框架，采用极紧凑的潜在图像嵌入作为扩散过程的条件。该方法显著降低传输开销，将传输嵌入压缩至原始图像大小的0.29%。在多个评估指标下，其重建质量优于三个基准方法——基于分割图的扩散SIC模型（GESCO）、近期基于Stable Diffusion（SD）的SIC框架（Img2Img-SC），以及传统的JPEG2000 + LDPC编码。尤其在噪声信道中表现优异。此外，计算效率大幅提升：对于512×512图像，重建速度超过Img2Img-SC的3倍；对于1024×1024图像，提速超过16倍。
原文摘要 · Abstract (English)
Diffusion Model (DM) based Semantic Image Communication (SIC) systems face significant challenges, such as slow inference speed and generation randomness, that limit their reliability and practicality. To overcome these issues, we propose a novel SIC framework inspired by Stable Cascade, where extremely compact latent image embeddings are used as conditioning to the diffusion process. Our approach drastically reduces the data transmission overhead, compressing the transmitted embedding to just 0.29% of the original image size. It outperforms three benchmark approaches - the diffusion SIC model conditioned on segmentation maps (GESCO), the recent Stable Diffusion (SD)-based SIC framework (Img2Img-SC), and the conventional JPEG2000 + LDPC coding - by achieving superior reconstruction quality under noisy channel conditions, as validated across multiple metrics. Notably, it also delivers significant computational efficiency, enabling over 3x faster reconstruction for 512 x 512 images and more than 16x faster for 1024 x 1024 images as compared to the approach adopted in Img2Img-SC.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。