Neural Network Assisted Lifting Steps For Improved Fully Scalable Lossy Image Compression in JPEG 2000

TL;DR

This paper introduces neural network-assisted lifting steps into JPEG 2000's wavelet transform to reduce redundancy and enhance image quality, achieving significant compression savings while maintaining scalability.

Contribution

It presents a novel end-to-end trainable neural network approach integrated into wavelet lifting steps for scalable image compression in JPEG 2000.

Findings

Up to 17.4% average BD bit-rate savings.

Improved residual redundancy reduction and image quality.

Fully scalable system with shared network parameters.

Abstract

This work proposes to augment the lifting steps of the conventional wavelet transform with additional neural network assisted lifting steps. These additional steps reduce residual redundancy (notably aliasing information) amongst the wavelet subbands, and also improve the visual quality of reconstructed images at reduced resolutions. The proposed approach involves two steps, a high-to-low step followed by a low-to-high step. The high-to-low step suppresses aliasing in the low-pass band by using the detail bands at the same resolution, while the low-to-high step aims to further remove redundancy from detail bands, so as to achieve higher energy compaction. The proposed two lifting steps are trained in an end-to-end fashion; we employ a backward annealing approach to overcome the non-differentiability of the quantization and cost functions during back-propagation. Importantly, the networks employed in this paper are compact and with limited non-linearities, allowing a fully scalable system; one pair of trained network parameters are applied for all levels of decomposition and for all bit-rates of interest. By employing the proposed approach within the JPEG 2000 image coding standard, our method can achieve up to 17.4% average BD bit-rate saving over a wide range of bit-rates, while retaining quality and resolution scalability features of JPEG 2000.