Learned Neural Iterative Decoding for Lossy Image Compression Systems

Alexander G. Ororbia, Ankur Mali, Jian Wu, Scott O'Connell, William Dreese, David Miller, C. Lee Giles

Research output: Chapter in Book/Report/Conference proceedingConference contribution

16 Scopus citations


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.

Original languageEnglish (US)
Title of host publicationProceedings - DCC 2019
Subtitle of host publication2019 Data Compression Conference
EditorsMichael W. Marcellin, Ali Bilgin, James A. Storer, Joan Serra-Sagrista
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages10
ISBN (Electronic)9781728106571
StatePublished - May 10 2019
Event2019 Data Compression Conference, DCC 2019 - Snowbird, United States
Duration: Mar 26 2019Mar 29 2019

Publication series

NameData Compression Conference Proceedings
ISSN (Print)1068-0314


Conference2019 Data Compression Conference, DCC 2019
Country/TerritoryUnited States

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications


Dive into the research topics of 'Learned Neural Iterative Decoding for Lossy Image Compression Systems'. Together they form a unique fingerprint.

Cite this