AI Paper Atlas

Research map / Image generation / Super-resolution

Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks

Majed El Helou, Ruofan Zhou, Sabine Süsstrunk

ECCV 2020 · Image generation › Super-resolution · approach: Blind super-resolution · 43 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
add 50% SFM during trainingRCAN · DIV2K val x4, Gaussian g6.5 test kernelPSNR (dB): 21.72 -> 21.79Improved
add 50% SFM during trainingRRDB · DIV2K val x4, bicubicPSNR (dB): 28.79 -> 29.10Improved
add 50% SFM during trainingESRGAN · DIV2K val x4, Gaussian g6.5PSNR (dB): 19.42 -> 19.77Improved
add 50% SFM during trainingIKC · DIV2K val x4, unseen kernelsPSNR (dB): 22.08 -> 22.35Improved
add 50% SFM during trainingIKC · DIV2K val x4, bicubicPSNR (dB): 27.81 -> 27.78No clear effect
add 50% SFM during trainingKMSR · RealSR x4PSNR (dB): 28.27 -> 28.50Improved
add 50% SFM during trainingRCAN · SR-RAW x8PSNR (dB): 24.18 -> 24.50Improved
add 50% SFM during trainingMemNet · BSD68 AWGN noise level 100PSNR (dB): 17.16 -> 19.46Improved
add 50% SFM during trainingRIDNet · BSD68 AWGN noise level 10PSNR (dB): 33.65 -> 33.43Hurt
add 50% SFM during trainingN3Net · BSD68 AWGN noise level 10PSNR (dB): 33.53 -> 33.41Hurt
add 50% SFM during trainingDnCNN-B · BSD68 AWGN noise level 70PSNR (dB): 22.06 -> 22.80Improved
add 50% SFM during trainingNoise2Noise · Two-photon microscopy, 1 raw imagePSNR (dB): 32.70 -> 33.05Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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