Learning True Rate-Distortion-Optimization for End-To-End Image Compression

TL;DR

This paper introduces a novel training method for end-to-end image compression that incorporates rate-distortion optimization, resulting in significant rate savings and enabling adaptive compression strategies similar to traditional codecs.

Contribution

The paper presents a new training approach that integrates low-complexity RDO estimations and fast inference modes into end-to-end image compression models, improving efficiency and compression performance.

Findings

Achieved 19.6% MS-SSIM rate savings over previous RDONet

Attained 27.3% rate savings over conventional deep image codecs

Enhanced training with low-complexity RDO estimations improves compression efficiency

Abstract

Even though rate-distortion optimization is a crucial part of traditional image and video compression, not many approaches exist which transfer this concept to end-to-end-trained image compression. Most frameworks contain static compression and decompression models which are fixed after training, so efficient rate-distortion optimization is not possible. In a previous work, we proposed RDONet, which enables an RDO approach comparable to adaptive block partitioning in HEVC. In this paper, we enhance the training by introducing low-complexity estimations of the RDO result into the training. Additionally, we propose fast and very fast RDO inference modes. With our novel training method, we achieve average rate savings of 19.6% in MS-SSIM over the previous RDONet model, which equals rate savings of 27.3% over a comparable conventional deep image coder.