AI Paper Atlas

Research map / Image generation / Super-resolution

Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling

Jingyun Liang, Andreas Lugmayr, Kai Zhang, Martin Danelljan, Luc Van Gool, Radu Timofte

ICCV 2021 · Image generation › Super-resolution · approach: Perceptual and real-world SR · 123 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 conditional priors y2 and y1 (hierarchical conditioning) (ablation)HCFlow · DIV2K val x4 SRPSNR: 18.95 -> 28.71Improved
use hierarchical instead of single-scale conditional mechanism (ablation)HCFlow · DIV2K val x4 SRPSNR: 28.60 -> 28.71Improved
use hierarchical instead of single-scale conditional mechanism (ablation)HCFlow · DIV2K val x4 SRLPIPS (tau=0.9): 0.126 -> 0.124Improved
add LR image space y2 to the latent space (ablation)HCFlow without conditional priors · DIV2K val x4 SRPSNR: 4.76 -> 18.95Improved
use external ground-truth LR as prior instead of LR in latent space (ablation)HCFlow · DIV2K val x4 SRPSNR: 28.71 -> 28.73No clear effect
condition on ground-truth LR y* additionally to generated y2 (ablation)HCFlow · DIV2K val x4 SRPSNR: 28.71 -> 28.71No clear effect
add HR pixel loss (HCFlow+)HCFlow · DIV2K val x4 SRPSNR: 28.71 -> 29.25Improved
add perceptual and GAN loss (HCFlow++)HCFlow · DIV2K val x4 SRLPIPS: 0.124 -> 0.110Improved
raise sampling temperature from 0 to 0.9HCFlow · DIV2K val x4 SRLPIPS: 0.285 -> 0.124Improved
raise sampling temperature from 0 to 0.9HCFlow · DIV2K val x4 SRPSNR: 28.71 -> 27.02Hurt
use HCFlow instead of IRN for rescalingIRN · Set14 image rescaling x4PSNR: 32.67 -> 33.02Improved

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