GAN-Based Semantic Communication for Image Transmission in IoV
Computer Vision and Pattern Recognition
Summary
The authors propose a new way for vehicles to share visual information efficiently and clearly even when internet conditions are not perfect. They use a special type of neural network (called a generative adversarial network) to send important parts of images based on how important they are for driving safety. On receiving the data, the system reconstructs high-quality images from these simplified parts, making it easier to understand the surroundings. Their tests show better image quality and clearer scene understanding compared to older methods, and the system works reliably in noisy communication environments.
generative adversarial networksemantic communicationpyramid attention networksemantic segmentationimage reconstructionbit allocationperceptual lossCityscapes datasetAWGN channelRayleigh channel
Authors
Ruixing Ren, Shan Chen, Junhui Zhao, Xiaoke Sun
Abstract
For cooperative perception in the internet of vehicles, this paper proposes a generative adversarial network-based semantic communication framework to address the efficiency and fidelity bottlenecks of traditional communication systems in visual data transmission under limited bandwidth and dynamic channel conditions. At the transmitter, the framework adopts a pyramid attention network to extract semantic label maps and introduces a semantic priority preservation mechanism. It assigns differentiated weights to distinct semantic categories based on driving safety, guiding bit allocation and loss function design. At the receiver, an image reconstruction module integrating a coarse to-fine multi-resolution generator and multi-scale discriminator is designed. Combined with the temporal consistency branch, spatial pyramid pooling and class-aware convolutional layers, it achieves high-fidelity reconstruction of high-quality images from corrupted semantic labels. The model is trained with combined adversarial, feature matching and perceptual losses, effectively improving semantic consistency and visual realism of generated images. Experimental results on the Cityscapes dataset show that the proposed method outperforms existing counterparts in both semantic segmentation accuracy and reconstructed image quality, and maintains stable reconstruction performance under AWGN and Rayleigh channels.