Deep Joint Source-Channel Coding for Wireless Image Transmission

TL;DR

This paper introduces a deep neural network-based joint source-channel coding method for wireless image transmission that outperforms traditional digital schemes, especially at low SNR, and avoids the cliff effect through learned, noise-resilient representations.

Contribution

It presents a novel deep JSCC approach using CNNs that directly maps images to channel symbols, outperforming traditional digital methods and eliminating the cliff effect.

Findings

Outperforms JPEG/JPEG2000 with capacity-achieving codes at low SNR.

Does not suffer from cliff effect, providing graceful degradation.

Outperforms separation-based digital communication in Rayleigh fading channels.

Abstract

We propose a joint source and channel coding (JSCC) technique for wireless image transmission that does not rely on explicit codes for either compression or error correction; instead, it directly maps the image pixel values to the complex-valued channel input symbols. We parameterize the encoder and decoder functions by two convolutional neural networks (CNNs), which are trained jointly, and can be considered as an autoencoder with a non-trainable layer in the middle that represents the noisy communication channel. Our results show that the proposed deep JSCC scheme outperforms digital transmission concatenating JPEG or JPEG2000 compression with a capacity achieving channel code at low signal-to-noise ratio (SNR) and channel bandwidth values in the presence of additive white Gaussian noise (AWGN). More strikingly, deep JSCC does not suffer from the ``cliff effect'', and it provides a graceful performance degradation as the channel SNR varies with respect to the SNR value assumed during training. In the case of a slow Rayleigh fading channel, deep JSCC learns noise resilient coded representations and significantly outperforms separation-based digital communication at all SNR and channel bandwidth values.