JPEG Processing Neural Operator for Backward-Compatible Coding

TL;DR

The paper introduces JPNeO, a neural operator-based JPEG extension that enhances image quality and compatibility without altering the standard protocol, offering practical benefits like reduced memory and parameters.

Contribution

It presents a novel neural operator approach for JPEG that improves fidelity and compatibility, with empirical validation of high mutual information space.

Findings

Improved chroma preservation and reconstruction fidelity.

Reduced memory usage and parameter count.

Maintains backward compatibility with JPEG standard.

Abstract

Despite significant advances in learning-based lossy compression algorithms, standardizing codecs remains a critical challenge. In this paper, we present the JPEG Processing Neural Operator (JPNeO), a next-generation JPEG algorithm that maintains full backward compatibility with the current JPEG format. Our JPNeO improves chroma component preservation and enhances reconstruction fidelity compared to existing artifact removal methods by incorporating neural operators in both the encoding and decoding stages. JPNeO achieves practical benefits in terms of reduced memory usage and parameter count. We further validate our hypothesis about the existence of a space with high mutual information through empirical evidence. In summary, the JPNeO functions as a high-performance out-of-the-box image compression pipeline without changing source coding's protocol. Our source code is available at https://github.com/WooKyoungHan/JPNeO.