January 09, 2021
Super-resolution aims at increasing the resolution and level of detail within an image. The current state of the art in general single-image super-resolution is held by NESRGAN+, which injects a Gaussian noise after each residual layer at training time. In this paper, we harness evolutionary methods to improve NESRGAN+ by optimizing the noise injection at inference time. More precisely, we use Diagonal CMA to optimize the injected noise according to a novel criterion combining quality assessment and realism. Our results are validated by the PIRM perceptual score and a human study. Our method outperforms NESRGAN+ on several standard super-resolution datasets. More generally, our approach can be used to optimize any method based on noise injection.
Written by
Baptiste Rozière
Camille Couprie
Olivier Teytaud
Andry Rasoanaivo
Hanhe Lin
Nathanaël Carraz Rakotonirina
Vlad Hosu
Publisher
ICPR
Research Topics
December 15, 2021
Akash Bharadwaj, Graham Cormode
December 15, 2021
December 06, 2021
Bilal Alsallakh, Narine Kokhlikyan, Vivek Miglani, Shubham Muttepawar, Edward Wang (AI Infra), Sara Zhang, David Adkins, Orion Reblitz-Richardson
December 06, 2021
December 06, 2021
Tete Xiao, Mannat Singh, Eric Mintun, Trevor Darrell, Piotr Dollar, Ross Girshick
December 06, 2021
November 09, 2021
Diane Bouchacourt, Mark Ibrahim, Ari Morcos
November 09, 2021