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

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… (More)

Topics

12 Figures and Tables

Cite this paper

@article{Johnston2017ImprovedLI, title={Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks}, author={Nick Johnston and Damien Vincent and David Minnen and Michele Covell and Saurabh Singh and Troy T. Chinen and Sung Jin Hwang and Joel Shor and George Toderici}, journal={CoRR}, year={2017}, volume={abs/1703.10114} }