Region-of-Interest-Guided Deep Joint Source-Channel Coding for Image Transmission

Abstract: Deep joint source-channel coding (deepJSCC) and semantic communication have shown promising improvements in communication performance over wireless networks. However, current approaches primarily focus on enhancing average performance metrics, such as overall image reconstruction quality or task accuracy, which may not fully align with users' actual experience -- often driven by the quality of specific regions of interest (ROI). Motivated by this, we propose ROI-guided joint source-channel coding (ROI-JSCC), a novel deepJSCC framework that prioritizes high-quality transmission of ROI. The ROI-JSCC consists of four key components: (1) ROI embedding and feature map extraction, (2) ROI-guided split processing, (3) ROI-based loss function design, and (4) ROI-adaptive bandwidth allocation. Together, these components enable ROI-JSCC to selectively improve the reconstruction quality of varying ROI while preserving overall image quality without increasing computational burden. Experimental results under diverse communication environments demonstrate that ROI-JSCC significantly improves ROI reconstruction quality while maintaining competitive average image quality compared to recent state-of-the-art methods. All codes are available at https://github.com/hansung-choi/ROI-JSCC.