# Successive Refinement of Images with Deep Joint Source-Channel Coding

## TL;DR

This paper proposes deep learning-based joint source-channel coding methods for progressive image transmission over wireless channels, demonstrating improved robustness and layered representation capabilities compared to traditional digital techniques.

## Contribution

It introduces three deep JSCC strategies for successive image refinement, showing their effectiveness and near successively refinable nature in wireless communication.

## Key findings

- Deep JSCC offers graceful degradation with SNR.
- It outperforms traditional digital methods in low SNR and bandwidth.
- Layered representations achieve performance close to single-layer schemes.

## Abstract

We introduce deep learning based communication methods for successive refinement of images over wireless channels. We present three different strategies for progressive image transmission with deep JSCC, with different complexity-performance trade-offs, all based on convolutional autoencoders. Numerical results show that deep JSCC not only provides graceful degradation with channel signal-to-noise ratio (SNR) and improved performance in low SNR and low bandwidth regimes compared to state-of-the-art digital communication techniques, but can also successfully learn a layered representation, achieving performance close to a single-layer scheme. These results suggest that natural images encoded with deep JSCC over Gaussian channels are almost successively refinable.