Forward Error Correction applied to JPEG-XS codestreams

TL;DR

This paper investigates applying Forward Error Correction to JPEG-XS streams over lossy networks, proposing an adaptive protection scheme that significantly reduces image distortion at moderate loss rates.

Contribution

It introduces a rate-distortion optimized unequal error protection method for JPEG-XS, adapting Reed-Solomon redundancy based on loss type and rate.

Findings

Reduces Mean Squared Error by up to 92% at 5% loss rate

Demonstrates effectiveness of adaptive FEC over equal protection

Highlights differential impact of loss on JPEG-XS components

Abstract

JPEG-XS offers low complexity image compression for applications with constrained but reasonable bit-rate, and low latency. Our paper explores the deployment of JPEG-XS on lossy packet networks. To preserve low latency, Forward Error Correction (FEC) is envisioned as the protection mechanism of interest. Despite the JPEG-XS codestream is not scalable in essence, we observe that the loss of a codestream fraction impacts the decoded image quality differently, depending on whether this codestream fraction corresponds to codestream headers, to coefficients significance information, or to low/high frequency data, respectively. Hence, we propose a rate-distortion optimal unequal error protection scheme that adapts the redundancy level of Reed-Solomon codes according to the rate of channel losses and the type of information protected by the code. Our experiments demonstrate that, at 5% loss rates, it reduces the Mean Squared Error by up to 92% and 65%, compared to a transmission without and with optimal but equal protection, respectively.