Wireless End-to-End Image Transmission System Using Semantic Communications

TLDR

Semantic communication, which transmits meaning rather than raw bits, is seen as the future of mobile communication and is enabled by integrating AI technologies with 6G networks. This study implements a semantic communication–based end‑to‑end image transmission system to address bandwidth limitations in high‑volume multimedia applications and explores design considerations with physical channel characteristics. The system encodes images via semantic segmentation at the transmitter, transmits the segmented map, and decodes it at the receiver using a pre‑trained GAN trained on the COCO‑Stuff dataset, while also evaluating the impact of channel distortions and quantization noise. The approach yields substantial bandwidth savings compared to conventional transmission of full images, demonstrating the resource gains of semantic segmentation over ground‑truth image transmission.

Abstract

Semantic communication is considered the future of mobile communication, which aims to transmit data beyond Shannon's theorem of communications by transmitting the semantic meaning of the data rather than the bit-by-bit reconstruction of the data at the receiver's end. The semantic communication paradigm aims to bridge the gap of limited bandwidth problems in modern high-volume multimedia application content transmission. Integrating AI technologies with the 6G communications networks paved the way to develop semantic communication-based end-to-end communication systems. In this study, we have implemented a semantic communication-based end-to-end image transmission system, and we discuss potential design considerations in developing semantic communication systems in conjunction with physical channel characteristics. A Pre-trained GAN network is used at the receiver as the transmission task to reconstruct the realistic image based on the Semantic segmented image at the receiver input. The semantic segmentation task at the transmitter (encoder) and the GAN network at the receiver (decoder) is trained on a common knowledge base, the COCO-Stuff dataset. The research shows that the resource gain in the form of bandwidth saving is immense when transmitting the semantic segmentation map through the physical channel instead of the ground truth image in contrast to conventional communication systems. Furthermore, the research studies the effect of physical channel distortions and quantization noise on semantic communication-based multimedia content transmission.