Learned Neural Iterative Decoding for Lossy Image Compression Systems

TL;DR

This paper introduces an iterative neural decoding method for lossy image compression that enhances reconstruction quality by progressively reducing error, outperforming traditional codecs and neural models.

Contribution

It presents a recurrent neural network-based iterative refinement algorithm that improves decoder performance across any encoder, utilizing spatial context for better image reconstruction.

Findings

Achieves up to 0.871 dB gain over JPEG

Outperforms JPEG 2000 by 1.095 dB

Surpasses other neural models in perceptual quality

Abstract

For lossy image compression systems, we develop an algorithm, iterative refinement, to improve the decoder's reconstruction compared to standard decoding techniques. Specifically, we propose a recurrent neural network approach for nonlinear, iterative decoding. Our decoder, which works with any encoder, employs self-connected memory units that make use of causal and non-causal spatial context information to progressively reduce reconstruction error over a fixed number of steps. We experiment with variants of our estimator and find that iterative refinement consistently creates lower distortion images of higher perceptual quality compared to other approaches. Specifically, on the Kodak Lossless True Color Image Suite, we observe as much as a 0.871 decibel (dB) gain over JPEG, a 1.095 dB gain over JPEG 2000, and a 0.971 dB gain over a competitive neural model.