Image and Video Restoration and Compression Artefact Removal Using a NoGAN Approach

Filippo Mameli, Marco Bertini, Leonardo Galteri, Alberto Del Bimbo

Abstract

Lossy image and video compression algorithms introduce several types of visual artefacts that reduce the visual quality of the compressed media. In this work, we report results obtained using the NoGAN training approach and adapting the popular DeOldify architecture used for colorization, for image and video compression artefact removal and restoration.
BibTeX
@inproceedings{mameli2020image,
  author = {Filippo Mameli and Marco Bertini and Leonardo Galteri and Alberto Del Bimbo},
  title = {{Image and Video Restoration and Compression Artefact Removal Using a NoGAN Approach}},
  booktitle = {ACM Multimedia},
  year = {2020},
  doi = {10.1145/3394171.3414451},
}

Loading related content...

Figure