Evolutionary super-resolution

Rozière, Baptiste; Rakotonirina, Nathanaël Carraz; Hosu, Vlad; Rasoanaivo, Andry; Teytaud, Olivier

doi:10.1145/3377929.3389959

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2021

2022

Publication Types

Select...

Other1

Article1

Relationship

Self Cite1

Independent1

Authors

Journals

Cited by 2 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…according the PIRM perceptual index) and qualitatively (according to a human study). A short paper [39] presented the idea of merging super-resolution GAN and quality estimation. The present paper contains experimental results, equations and detailed algorithms.…”

Section: Introductionmentioning

confidence: 99%

Tarsier: Evolving Noise Injection in Super-Resolution GANs

Rozière

Rakotonirina

Hosu

et al. 2021

2020 25th International Conference on Pattern Recognition (ICPR)

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%