Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks

TL;DR

This paper introduces a novel recurrent neural network-based lossy image compression method that outperforms traditional codecs by employing SSIM-weighted loss, improved spatial diffusion, and adaptive bit allocation, achieving state-of-the-art results.

Contribution

The paper presents three key innovations: SSIM-weighted pixel loss, enhanced recurrent architecture for better spatial information flow, and spatially adaptive bit rates for improved compression efficiency.

Findings

Outperforms BPG, WebP, JPEG2000, JPEG in MS-SSIM

Effective spatial diffusion improves image reconstruction

Adaptive bit allocation enhances compression of complex regions

Abstract

We propose a method for lossy image compression based on recurrent, convolutional neural networks that outperforms BPG (4:2:0 ), WebP, JPEG2000, and JPEG as measured by MS-SSIM. We introduce three improvements over previous research that lead to this state-of-the-art result. First, we show that training with a pixel-wise loss weighted by SSIM increases reconstruction quality according to several metrics. Second, we modify the recurrent architecture to improve spatial diffusion, which allows the network to more effectively capture and propagate image information through the network's hidden state. Finally, in addition to lossless entropy coding, we use a spatially adaptive bit allocation algorithm to more efficiently use the limited number of bits to encode visually complex image regions. We evaluate our method on the Kodak and Tecnick image sets and compare against standard codecs as well recently published methods based on deep neural networks.