AI Paper Atlas

Research map / Image generation / Super-resolution

Content-Aware Local GAN for Photo-Realistic Super-Resolution

JoonKyu Park, Sanghyun Son, Kyoung Mu Lee

ICCV 2023 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 74 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
replace plain GAN discriminator with CAL-GAN mixture of classifiersEDSR · DIV2K (val) x4 SRLPIPS: 0.220 -> 0.074Improved
replace plain GAN discriminator with CAL-GANSwinIR · DIV2K (val) x4 SRLPIPS: 0.093 -> 0.087Improved
add balancing loss for routing (ablation)CAL-GAN · DIV2K (val) x4 SRLPIPS: 0.100 -> 0.091Improved
add orthogonal loss on classifier projections (ablation)CAL-GAN · DIV2K (val) x4 SRLPIPS: 0.109 -> 0.091Improved
add distribution (LDA-style) loss (ablation)CAL-GAN · DIV2K (val) x4 SRFID: 14.046 -> 11.772Improved
use 12 classifiers instead of 1 (ablation)CAL-GAN · DIV2K (val) x4 SRFID: 13.953 -> 11.772Improved
increase classifiers from 12 to 16 (ablation)CAL-GAN · DIV2K (val) x4 SRFID: 11.772 -> 12.520Hurt
use patch size 4 instead of 1 for class assignment (ablation)CAL-GAN · DIV2K (val) x4 SRFID: 14.116 -> 11.772Improved
use learned content-based routing instead of segmentation-based routing (ablation)CAL-GAN · DIV2K (val) x4 SRLPIPS: 0.137 -> 0.091Improved
CAL-GAN vs LDL on BSD100 FID with RRDB backboneRRDB · BSD100 x4 SRFID: 43.217 (CAL-GAN) vs 40.806 (LDL)Mixed
CAL-GAN vs LDL on distortion metricsRRDB · Urban100 x4 SRPSNR (dB): 25.498 (LDL) -> 25.290 (CAL-GAN)Hurt

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