Journal article

SVOBODA Pavel, HRADIŠ Michal, BAŘINA David and ZEMČÍK Pavel. Compression Artifacts Removal Using Convolutional Neural Networks. Journal of WSCG. Plzeň: 2016, vol. 24, no. 2, pp. 63-72. ISSN 1213-6972. Available from: https://dspace5.zcu.cz/handle/11025/21649
Publication language:english
Original title:Compression Artifacts Removal Using Convolutional Neural Networks
Title (cs):Odstranění kompresních artefaktů pomocí konvolučních neuronových sítí
Pages:63-72
Place:CZ
Year:2016
URL:https://dspace5.zcu.cz/handle/11025/21649
Journal:Journal of WSCG, Vol. 24, No. 2, Plzeň, CZ
ISSN:1213-6972
Files: 
+Type Name Title Size Last modified
iconfinal.pdfpublisher's version2,61 MB2016-07-11 16:23:11
^ Select all
With selected:
Keywords
Deep learning, Convolutional neural networks, JPEG, Compression artifacts, Deblocking, Deringing
Annotation
This paper shows that it is possible to train large and deep convolutional neural networks (CNN) for JPEG compression artifacts reduction.
Abstract
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.
BibTeX:
@ARTICLE{
   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 = {http://www.fit.vutbr.cz/research/view_pub.php.en.iso-8859-2?id=11176}
}

Your IPv4 address: 54.221.76.68
Switch to IPv6 connection

DNSSEC [dnssec]