AI Paper Atlas

Research map / Image generation / Super-resolution

To learn image super-resolution, use a GAN to learn how to do image degradation first

Adrian Bulat, Jing Yang, Georgios Tzimiropoulos

ECCV 2018 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 435 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
train Low-to-High on High-to-Low (learned degradation) output instead of bilinear downsampling (ablation)Low-to-High · Widerface real-world LR test setFID: 85.59 -> 14.89Improved
train Low-to-High on High-to-Low output instead of bilinear plus blur (ablation)Low-to-High · Widerface real-world LR test setFID: 84.68 -> 14.89Improved
add GAN loss to pixel loss when training Low-to-High on High-to-Low output (ablation)Low-to-High · Widerface real-world LR test setFID: 87.91 -> 14.89Improved
use learned High-to-Low degradation instead of bilinear downsampling to create LR imagesdegradation model · Widerface real-world LR test setFID to original LR: 23.15 -> 15.27Improved
add blurring before bilinear downsampling for training LR images (ablation)Low-to-High · Widerface real-world LR test setFID: 85.59 -> 84.68No clear effect
compare against SRGAN trained on bilinear pairsSRGAN · Widerface real-world LR test setFID: 104.80 -> 14.89Improved
compare against CycleGanCycleGan · Widerface real-world LR test setFID: 19.01 -> 14.89Improved
train Low-to-High on High-to-Low output instead of bilinear downsampling (ablation)Low-to-High · LS3D-W (bilinear input)PSNR: 23.50 -> 19.30Hurt
train with pixel loss plus GAN loss instead of pixel loss only on LS3D-W bilinear input (ablation)Low-to-High · LS3D-W (bilinear input)PSNR: 23.22 -> 19.30Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 2 on most shared results.

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