AI Paper Atlas

Research map / Image generation / Super-resolution

Beyond the Ground Truth: Enhanced Supervision for Image Restoration

Donghun Ryou, Inju Ha, Sanghyeok Chu, Bohyung Han

CVPR 2026 · Image generation › Super-resolution · approach: Real-world super-resolution · 2 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 ORNet on top of FFTformerFFTformer · GoPro deblurringMUSIQ: 46.47 -> 64.57Improved
add ORNet on top of AdaRevDAdaRevD · GoPro deblurringA-FINE: 36.19 -> 14.38Improved
add ORNet on top of NAFNetNAFNet · SIDD denoisingMUSIQ: 22.73 -> 35.87Improved
add ORNet on top of FFTformer under extra Gaussian blurFFTformer · GoPro OOD (extra Gaussian blur)MUSIQ: 22.3812 -> 42.9131Improved
attach ORNet instead of finetuning with enhanced supervision (ablation)FFTformer · GoPro deblurringMUSIQ: 60.54 -> 64.57Improved
finetune FFTformer on enhanced ground truth (ablation)FFTformer · GoPro deblurringMUSIQ: 46.47 -> 60.54Improved
use mixed 2x, 3x, 4x GT variants instead of only the 4x variant (ablation)ORNet · GoPro deblurringMUSIQ: 62.81 -> 64.57Improved
increase enhancement level lambda from 0.1 to 0.9 (ablation)ORNet on FFTformer · GoPro deblurringMUSIQ: 48.07 -> 69.76Improved
increase lambda from 0.3 to 0.9 (ablation)ORNet on FFTformer · GoPro deblurringVisualQuality-R1: 4.1995 -> 3.9600Hurt
increase lambda from 0.3 to 0.9 under extra Gaussian blur (ablation)ORNet on FFTformer · GoPro OOD (extra Gaussian blur)PSNR (original GT): 24.5774 -> 24.2407Hurt
use 25 Gaussian ring bases instead of 5 (ablation)frequency mask generator · GoPro deblurring (qualitative)frequency control: B=5 -> B=25Improved
refine with ORNet instead of applying the OSEDiff ISR model directly (ablation)AdaRevD · GoPro deblurring (qualitative)hallucinationImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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