Neural JPEG: End-to-End Image Compression Leveraging a Standard JPEG Encoder-Decoder

TL;DR

Neural JPEG introduces a hybrid neural approach that enhances standard JPEG compression by optimizing DCT coefficients and jointly learning quantization tables, resulting in improved image quality and compression efficiency.

Contribution

It presents a novel method that improves JPEG compression by integrating neural network-based frequency domain editing and learned quantization tables, maintaining compatibility with standard encoders.

Findings

Outperforms JPEG in PSNR and MS-SSIM metrics

Produces visually appealing images with better color retention

Enhances compression performance without requiring non-standard encoders

Abstract

Recent advances in deep learning have led to superhuman performance across a variety of applications. Recently, these methods have been successfully employed to improve the rate-distortion performance in the task of image compression. However, current methods either use additional post-processing blocks on the decoder end to improve compression or propose an end-to-end compression scheme based on heuristics. For the majority of these, the trained deep neural networks (DNNs) are not compatible with standard encoders and would be difficult to deply on personal computers and cellphones. In light of this, we propose a system that learns to improve the encoding performance by enhancing its internal neural representations on both the encoder and decoder ends, an approach we call Neural JPEG. We propose frequency domain pre-editing and post-editing methods to optimize the distribution of the DCT coefficients at both encoder and decoder ends in order to improve the standard compression (JPEG) method. Moreover, we design and integrate a scheme for jointly learning quantization tables within this hybrid neural compression framework.Experiments demonstrate that our approach successfully improves the rate-distortion performance over JPEG across various quality metrics, such as PSNR and MS-SSIM, and generates visually appealing images with better color retention quality.