SNR-adaptive deep joint source-channel coding for wireless image transmission

TL;DR

This paper introduces a novel deep joint source-channel coding scheme for wireless image transmission that adaptively adjusts to varying SNRs, enhancing robustness and multi-user applicability.

Contribution

It presents the first deep JSCC scheme that adapts to different SNRs and supports multi-user scenarios, improving transmission robustness.

Findings

Achieves high adaptability to varying SNRs

Robust to SNR estimation errors

Applicable to multi-user wireless image transmission

Abstract

Considering the problem of joint source-channel coding (JSCC) for multi-user transmission of images over noisy channels, an autoencoder-based novel deep joint source-channel coding scheme is proposed in this paper. In the proposed JSCC scheme, the decoder can estimate the signal-to-noise ratio (SNR) and use it to adaptively decode the transmitted image. Experiments demonstrate that the proposed scheme achieves impressive results in adaptability for different SNRs and is robust to the decoder's estimation error of the SNR. To the best of our knowledge, this is the first deep JSCC scheme that focuses on the adaptability for different SNRs and can be applied to multi-user scenarios.