Video compression algorithms result in a reduction of image quality, because of their lossy approach to reduce the required bandwidth. This affects commercial streaming services such as Netflix, or Ama- zon Prime Video, but affects also video conferencing and video surveillance systems. In all these cases it is possible to improve the video quality, both for human view and for automatic video analysis, without changing the compression pipeline, through a post-processing that eliminates the visual artifacts created by the compression algorithms. Generative Adversarial Networks have obtained extremely high quality results in image enhancement tasks; however, to obtain such results large generators are usually employed, resulting in high computational costs and processing time. In this work we present an architecture that can be used to reduce the computational cost and that has been implemented on mobile devices. A possible application is to improve video conferencing, or live streaming. In these cases there is no original uncompressed video stream available. Therefore, we report results using no-reference video quality metric showing high naturalness and quality even for efficient networks.

Fast Video Quality Enhancement using GANs / Galteri, Leonardo; Seidenari, Lorenzo; Bertini, Marco; Uricchio, Tiberio; Del Bimbo, Alberto. - ELETTRONICO. - (2019), pp. 1065-1067. (Intervento presentato al convegno ACM Multimedia) [10.1145/3343031.3350592].

Fast Video Quality Enhancement using GANs

Galteri, Leonardo;Seidenari, Lorenzo;Bertini, Marco;Uricchio, Tiberio;Del Bimbo, Alberto
2019

Abstract

Video compression algorithms result in a reduction of image quality, because of their lossy approach to reduce the required bandwidth. This affects commercial streaming services such as Netflix, or Ama- zon Prime Video, but affects also video conferencing and video surveillance systems. In all these cases it is possible to improve the video quality, both for human view and for automatic video analysis, without changing the compression pipeline, through a post-processing that eliminates the visual artifacts created by the compression algorithms. Generative Adversarial Networks have obtained extremely high quality results in image enhancement tasks; however, to obtain such results large generators are usually employed, resulting in high computational costs and processing time. In this work we present an architecture that can be used to reduce the computational cost and that has been implemented on mobile devices. A possible application is to improve video conferencing, or live streaming. In these cases there is no original uncompressed video stream available. Therefore, we report results using no-reference video quality metric showing high naturalness and quality even for efficient networks.
2019
Proceedings of the 27th ACM International Conference on Multimedia
ACM Multimedia
Galteri, Leonardo; Seidenari, Lorenzo; Bertini, Marco; Uricchio, Tiberio; Del Bimbo, Alberto
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1177903
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 11
  • ???jsp.display-item.citation.isi??? 7
social impact