AI Paper Atlas

Research map / Image generation / Super-resolution

Fourier Space Losses for Efficient Perceptual Image Super-Resolution

Dario Fuoli, Luc Van Gool, Radu Timofte

ICCV 2021 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 206 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
use Fourier supervision loss instead of L1 (ablation)IMDN · DIV2K val (loss ablation, 4x)LPIPS: 0.270 -> 0.189Improved
use Fourier supervision loss instead of L1 (ablation)IMDN · DIV2K val (loss ablation, 4x)PSNR: 30.56 -> 29.53Hurt
add Fourier supervision loss to L1 (ablation)IMDN · DIV2K val (loss ablation, 4x)FID: 22.91 -> 21.96Improved
replace ESRGAN spatial losses with Fourier losses (ablation)IMDN · DIV2K val (loss ablation, 4x)PSNR: 27.94 -> 29.06Improved
replace ESRGAN spatial losses with Fourier losses (ablation)IMDN · DIV2K val (loss ablation, 4x)LPIPS: 0.131 -> 0.129No clear effect
add Fourier losses on top of spatial losses (ablation)IMDN · DIV2K val (loss ablation, 4x)FID: 17.07 -> 15.88Improved
add Fourier GAN loss (ablation)IMDN · DIV2K val (loss ablation, 4x)FID: 16.94 -> 15.88Improved
add spatial GAN loss alongside Fourier GAN (ablation)IMDN · DIV2K val (loss ablation, 4x)FID: 17.90 -> 15.88Improved
add Fourier losses to ESRGAN generator (ablation)ESRGAN · DIV2K val (loss ablation, 4x)FID: 15.37 -> 14.80Improved
add Fourier losses to ESRGAN generatorESRGAN · Urban100FID: 25.50 -> 24.07Improved
add Fourier losses to ESRGAN generatorESRGAN · BSD100FID: 60.42 -> 57.90Improved
use Fourier losses instead of WaveletSRNet lossesIMDN · DIV2K val (comparison with state of the art)FID: 19.80 -> 15.72Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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