Publication Details

Compression Artifacts Removal Using Convolutional Neural Networks

SVOBODA Pavel, HRADIŠ Michal, BAŘINA David and ZEMČÍK Pavel. Compression Artifacts Removal Using Convolutional Neural Networks. Journal of WSCG, vol. 24, no. 2, 2016, pp. 63-72. ISSN 1213-6972. Available from: https://dspace5.zcu.cz/handle/11025/21649
Czech title
Odstranění kompresních artefaktů pomocí konvolučních neuronových sítí
Type
journal article
Language
english
Authors
URL
Keywords

Deep learning, Convolutional neural networks, JPEG, Compression artifacts, Deblocking, Deringing

Abstract

This paper shows that it is possible to train large and deep convolutional neural networks (CNN) for JPEG compression artifacts reduction.

Annotation

This paper shows that it is possible to train large and deep convolutional neural networks (CNN) for JPEG compression artifacts reduction, and that such networks can provide significantly better reconstruction quality compared to previously used smaller networks as well as to any other state-of-the-art methods. We were able to train networks with 8 layers in a single step and in relatively short time by combining residual learning, skip architecture, and symmetric weight initialization. We provide further insights into convolution networks for JPEG artifact reduction by evaluating three different objectives, generalization with respect to training dataset size, and generalization with respect to JPEG quality level.

Published
2016
Pages
63-72
Journal
Journal of WSCG, vol. 24, no. 2, ISSN 1213-6972
EID Scopus
BibTeX
@ARTICLE{FITPUB11176,
   author = "Pavel Svoboda and Michal Hradi\v{s} and David Ba\v{r}ina and Pavel Zem\v{c}\'{i}k",
   title = "Compression Artifacts Removal Using Convolutional Neural Networks",
   pages = "63--72",
   journal = "Journal of WSCG",
   volume = 24,
   number = 2,
   year = 2016,
   ISSN = "1213-6972",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11176"
}
Files
Back to top