Efficient and Robust Semantic Image Communication via Stable Cascade

TL;DR

This paper introduces a stable cascade-based semantic image communication framework that uses extremely compact latent embeddings, significantly reducing data transmission and achieving faster, more reliable image reconstruction under noisy conditions.

Contribution

The proposed framework employs a novel stable cascade approach with compact latent embeddings, improving transmission efficiency and reconstruction quality over existing diffusion-based SIC methods.

Findings

Reduces data transmission to 0.29% of original image size.

Achieves superior reconstruction quality under noisy channels.

Enables over 3x faster reconstruction for 512x512 images.

Abstract

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.