CASC: Condition-Aware Semantic Communication with Latent Diffusion Models
Authors:
- 8 June 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1723-1728
Abstract
Diffusion-based semantic communication methods have shown significant advantages in image transmission by harnessing the generative power of diffusion models. However, they still face challenges, including generation randomness that leads to distorted reconstructions and high computational costs. To address these issues, we propose CASC, a condition-aware semantic communication framework that incorporates a latent diffusion model (LDM)-based denoiser. The LDM denoiser at the receiver utilizes the received noisy latent codes as the conditioning signal to reconstruct the latent codes, enabling the decoder to accurately recover the source image. By operating in the latent space, the LDM reduces computational complexity compared to traditional diffusion models (DMs). Additionally, we introduce a condition-aware neural network (CAN) that dynamically adjusts the weights in the hidden layers of the LDM based on the conditioning signal. This enables finer control over the generation process, significantly improving the perceptual quality of the reconstructed images. Experimental results show that CASC significantly outperforms DeepJSCC in both perceptual quality and visual effect. Moreover, CASC reduces inference time by 51.7% compared to existing DM-based semantic communication systems, while maintaining comparable perceptual performance. The ablation studies also validate the effectiveness of the CAN module in improving the image reconstruction quality.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Condition-Aware Neural Network for Controlled Image Generation2024
- DIFFSC: Semantic Communication Framework With Enhanced Denoising Through Diffusion Probabilistic Models2024
- Generative Model based Highly Efficient Semantic Communication Approach for Image Transmission2023
- Semantic Communications for Future Internet: Fundamentals, Applications, and ChallengesIEEE Communications Surveys & Tutorials, 2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Deep Learning-Based Image Semantic Coding for Semantic Communications2021
- Taming Transformers for High-Resolution Image Synthesis2021
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- A Mathematical Theory of CommunicationBell System Technical Journal, 1948