Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks
Authors:
- Nick JohnstonNJNick Johnston
- Damien VincentDVDamien Vincent
- David MinnenDMDavid Minnen
- Michele CovellMCMichele Covell
- Saurabh SinghSSSaurabh Singh
- Troy ChinenTCTroy Chinen
- Sung Jin HwangSHSung Jin Hwang
- Joel ShorJSJoel Shor
- George TodericiGTGeorge Toderici
Top Cited Papers
- 1 June 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4385-4393
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 using a single model. First, 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. Second, 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. Finally, we show that training with a pixel-wise loss weighted by SSIM increases reconstruction quality according to multiple metrics. We evaluate our method on the Kodak and Tecnick image sets and compare against standard codecs as well as recently published methods based on deep neural networks.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Multiple hypothesis colorization and its application to image compressionComputer Vision and Image Understanding, 2017
- Spatially adaptive image compression using a tiled deep network2017
- Full Resolution Image Compression with Recurrent Neural Networks2017
- Loss Functions for Image Restoration With Neural NetworksIEEE Transactions on Computational Imaging, 2016
- Communicating Pictures—The Future2014
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Image compression with neural networks – A surveySignal Processing: Image Communication, 1999
- The JPEG still picture compression standardCommunications of the ACM, 1991