AI Paper Atlas

Research map / Image generation / Super-resolution

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution

Kai Zhang, Jingyun Liang, Luc Van Gool, Radu Timofte

ICCV 2021 · Image generation › Super-resolution · approach: Blind super-resolution · 883 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 with the proposed shuffled degradation model instead of bicubic degradationESRGAN architecture · DIV2K4D Type IVLPIPS: 0.599 -> 0.361Improved
train with the proposed shuffled degradation model instead of bicubic degradationESRGAN architecture · DIV2K4D Type IVPSNR (Y, dB): 23.68 -> 24.58Improved
train with the proposed shuffled degradation model instead of bicubic degradationESRGAN architecture · DIV2K4D Type IILPIPS: 0.526 -> 0.284Improved
train with the proposed shuffled degradation model instead of bicubic degradationESRGAN architecture · DIV2K4D Type I (bicubic)PSNR (Y, dB): 28.16 -> 27.30Hurt
train with the proposed shuffled degradation model instead of bicubic degradationESRGAN architecture · DIV2K4D Type I (bicubic)LPIPS: 0.115 -> 0.236Hurt
train with the proposed degradation model (PSNR-oriented BSRNet vs RRDB)RRDB architecture · DIV2K4D Type IVPSNR (Y, dB): 24.03 -> 25.67Improved
train with the proposed degradation model (PSNR-oriented BSRNet vs RRDB)RRDB architecture · DIV2K4D Type I (bicubic)PSNR (Y, dB): 30.89 -> 29.07Hurt
add GAN and perceptual losses (BSRGAN vs BSRNet)BSRNet · DIV2K4D Type IVPSNR (Y, dB): 25.67 -> 24.58Hurt
add GAN and perceptual losses (BSRGAN vs BSRNet)BSRNet · DIV2K4D Type IVLPIPS: 0.506 -> 0.361Improved
train with the proposed degradation model, evaluated with no-reference IQAESRGAN architecture · RealSRSetNIQE: 4.95 -> 5.60Hurt
train with the proposed degradation model, evaluated with no-reference IQAESRGAN architecture · RealSRSetPI: 4.47 -> 4.72Hurt
train with the proposed degradation model, evaluated with no-reference IQAESRGAN architecture · RealSRSetNRQM: 6.02 -> 6.17Improved

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