AI Paper Atlas

Research map / Image generation / Super-resolution

Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution

Yuehan Zhang, Bo Ji, Jia Hao, Angela Yao

ECCV 2022 · Image generation › Super-resolution · approach: Real-world super-resolution · 18 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
use one-shot single model instead of fusing separately trained models with style-transfer post-processingLFc-SR vs WDST · Inference 128x128 LR, x4total run-time: ≈1153s -> 0.566sImproved
use one-shot single model instead of WDST post-processingLFc-SR vs WDST · Inference 128x128 LR, x4total FLOPs: ≈37500.3M -> 26.8MImproved
add PD-ADMM optimization versus regularizer-weight training (ablation)LFc-SR · BSD100 and Urban100 PD planeperception-distortion balanceImproved
add low-frequency constraint (versus lambda_r=0) (ablation)LFc-SR · BSD100 and Urban100LF similarity between stagesImproved
increase regularizer weight lambda_r (ablation)regularizer-based LFc-SR · BSD100 and Urban100perceptual vs objective qualityMixed
use O-P stage order (objective first) instead of swapped P-O order with HF constraint (ablation)LFc-SR · Urban100 and Manga109 PD planePD trade-offImproved
extract LF subband with Gaussian blur instead of DWT (ablation)LFc-SR · PD trade-off planePD trade-offNo clear effect

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