AI Paper Atlas

Research map / Image generation / Super-resolution

SRFlow: Learning the Super-Resolution Space with Normalizing Flow

Andreas Lugmayr, Martin Danelljan, Luc Van Gool, Radu Timofte

ECCV 2020 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 409 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
pretrain the LR-Encoder (ablation)SRFlow · CelebA 8xPSNR: 25.06 -> 25.24Improved
pretrain the LR-Encoder (ablation)SRFlow · CelebA 8xLPIPS: 0.108 -> 0.110No clear effect
use SRFlow instead of ESRGANSRFlow · CelebA 8x (bicubic)PSNR: 22.88 -> 25.24Improved
use SRFlow instead of ESRGANSRFlow · DIV2K 4xPSNR: 26.22 -> 27.09Improved
use SRFlow instead of ESRGANSRFlow · DIV2K 8xPSNR: 22.18 -> 23.05Improved
lower sampling temperature to tau=0 (ablation)SRFlow · DIV2K / CelebAPSNR: similar PSNR to RRDB for tau=0Mixed
raise sampling temperature to tau >= 0.8 (ablation)SRFlow · perception-distortionLPIPS: similar or better perceptual quality than ESRGAN for tau >= 0.8Improved
select best of n=1..10 samples (oracle) (ablation)SRFlow tau=0.8 · CelebA test 5000 imagesLPIPSImproved
apply latent space normalization for restorationSRFlow · DIV2K denoising sigma=20PSNR: 22.48 -> 27.81Improved
apply latent space normalization for restorationSRFlow · CelebA denoising sigma=20PSNR: 22.52 -> 27.62Improved
super-resolve noisy image without normalizationSRFlow · DIV2K denoising sigma=20PSNR: 22.48 -> 23.19Improved

Later papers that compared with this method

3 later accepted papers report SRFlow as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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