AI Paper Atlas

Research map / Image generation / GANs

SinGAN: Learning a Generative Model From a Single Natural Image

Tamar Rott Shaham, Tali Dekel, Tomer Michaeli

ICCV 2019 · Image generation › GANs · approach: Large-scale GAN latent analysis · 968 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
start generation from scale N-1 instead of the coarsest scale N (paired) (ablation)SinGAN · AMT Real/Fake pairedconfusion rate: 21.45% -> 30.45%Improved
start generation from scale N-1 instead of N (unpaired) (ablation)SinGAN · AMT Real/Fake unpairedconfusion rate: 42.9% -> 47.04%Improved
start generation from scale N-1 instead of N (ablation)SinGAN · single-image SIFIDSIFID: 0.09 -> 0.05Improved
start generation from scale N-1 instead of N (ablation)SinGAN · sample diversitynormalized pixel std: 0.5 -> 0.35Hurt
train with more pyramid scales (ablation)SinGAN · qualitative single imagesglobal structure preservationImproved
use SinGAN (internal, single image) instead of ZSSR for super-resolutioninternal SR methods · BSD100 super-resolutionNIQE: 7.13 -> 3.71Improved
use SinGAN instead of DIP for super-resolutioninternal SR methods · BSD100 super-resolutionNIQE: 6.35 -> 3.71Improved
use SinGAN instead of ZSSR for super-resolutioninternal SR methods · BSD100 super-resolutionRMSE: 13.08 -> 16.22Hurt
use SinGAN instead of EDSR for super-resolutionSR methods · BSD100 super-resolutionNIQE: 6.50 -> 3.71Improved
use SinGAN instead of SRGAN for super-resolutionSR methods · BSD100 super-resolutionNIQE: 3.41 vs 3.71No clear effect

Later papers that compared with this method

13 later accepted papers report SinGAN as a baseline in their results tables; 13 of them report a better number on most of the results they share with it.

5 more not listed.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy