Robust End-to-End Image Transmission with Residual Learning

TL;DR

This paper introduces a layered application layer image transmission scheme that uses residual learning to enhance robustness against end-to-end channel errors, offering a practical alternative to physical layer solutions.

Contribution

It proposes a novel layered transmission method at the application layer utilizing residual learning to improve robustness in image transmission over noisy channels.

Findings

High robustness to end-to-end channel errors demonstrated

Layered scheme effectively transmits coarse and residual images

Aligns residual representation with channel structure

Abstract

Recently, deep learning (DL) based image transmission at the physical layer (PL) has become a rising trend due to its ability to significantly outperform conventional separation-based digital transmissions. However, implementing solutions at the PL requires a major shift in established standards, such as those in cellular communications. Application layer (AL) solutions present a more feasible and standards-compliant alternative. In this work, we propose a layered image transmission scheme at the AL that is robust to end-to-end (E2E) channel errors. The base layer transmits a coarse image, while the enhancement layer transmits the residual between the original and coarse images. By mapping the residual image into a latent representation that aligns with the structure of the E2E channel, our proposed solution demonstrates high robustness to E2E channel errors.