English

Tarsier: Evolving Noise Injection in Super-Resolution GANs

Computer Vision and Pattern Recognition 2020-09-28 v1 Machine Learning Image and Video Processing

Abstract

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.

Keywords

Cite

@article{arxiv.2009.12177,
  title  = {Tarsier: Evolving Noise Injection in Super-Resolution GANs},
  author = {Baptiste Roziere and Nathanal Carraz Rakotonirina and Vlad Hosu and Andry Rasoanaivo and Hanhe Lin and Camille Couprie and Olivier Teytaud},
  journal= {arXiv preprint arXiv:2009.12177},
  year   = {2020}
}
R2 v1 2026-06-23T18:47:36.210Z