Latent Feature-Guided Conditional Diffusion for Generative Image Semantic Communication
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913880398102528 |
|---|---|
| author | Chen, Zehao Wei, Xinfeng Tong, Haonan Yang, Zhaohui Yin, Changchuan |
| author_facet | Chen, Zehao Wei, Xinfeng Tong, Haonan Yang, Zhaohui Yin, Changchuan |
| contents | Semantic communication is proposed and expected to improve the efficiency of massive data transmission over sixth generation (6G) networks. However, existing image semantic communication schemes are primarily focused on optimizing pixel-level metrics, while neglecting the crucial aspect of region of interest (ROI) preservation. To address this issue, we propose an ROI-aware latent representation-oriented image semantic communication (LRISC) system. In particular, we first map the source image to latent features in a high-dimensional semantic space, these latent features are then fused with ROI mask through a feature-weighting mechanism. Subsequently, these features are encoded using a joint source and channel coding (JSCC) scheme with adaptive rate for efficient transmission over a wireless channel. At the receiver, a conditional diffusion model is developed by using the received latent features as conditional guidance to steer the reverse diffusion process, progressively reconstructing high-fidelity images while preserving semantic consistency. Moreover, we introduce a channel signal-to-noise ratio (SNR) adaptation mechanism, allowing one model to work across various channel states. Experiments show that the proposed method significantly outperforms existing methods, in terms of learned perceptual image patch similarity (LPIPS) and robustness against channel noise, with an average LPIPS reduction of 43.3% compared to DeepJSCC, while guaranteeing the semantic consistency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_21577 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Latent Feature-Guided Conditional Diffusion for Generative Image Semantic Communication Chen, Zehao Wei, Xinfeng Tong, Haonan Yang, Zhaohui Yin, Changchuan Multimedia Semantic communication is proposed and expected to improve the efficiency of massive data transmission over sixth generation (6G) networks. However, existing image semantic communication schemes are primarily focused on optimizing pixel-level metrics, while neglecting the crucial aspect of region of interest (ROI) preservation. To address this issue, we propose an ROI-aware latent representation-oriented image semantic communication (LRISC) system. In particular, we first map the source image to latent features in a high-dimensional semantic space, these latent features are then fused with ROI mask through a feature-weighting mechanism. Subsequently, these features are encoded using a joint source and channel coding (JSCC) scheme with adaptive rate for efficient transmission over a wireless channel. At the receiver, a conditional diffusion model is developed by using the received latent features as conditional guidance to steer the reverse diffusion process, progressively reconstructing high-fidelity images while preserving semantic consistency. Moreover, we introduce a channel signal-to-noise ratio (SNR) adaptation mechanism, allowing one model to work across various channel states. Experiments show that the proposed method significantly outperforms existing methods, in terms of learned perceptual image patch similarity (LPIPS) and robustness against channel noise, with an average LPIPS reduction of 43.3% compared to DeepJSCC, while guaranteeing the semantic consistency. |
| title | Latent Feature-Guided Conditional Diffusion for Generative Image Semantic Communication |
| topic | Multimedia |
| url | https://arxiv.org/abs/2504.21577 |