AI Paper Atlas

Research map / Image generation / Super-resolution

SRFeat: Single Image Super-Resolution with Feature Discrimination

Seong-Jin Park, Hyeongseok Son, Sunghyun Cho, Ki-Sang Hong, Seungyong Lee

ECCV 2018 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 213 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 feature GAN loss (feature discriminator) to SRFeatI (ablation)SRFeatI · ILSVRC2016 val, ResNet-50 on SR imagesTop-5 error (%): 11.9 -> 11.0Improved
add feature GAN loss (feature discriminator) to SRFeatI (ablation)SRFeatI · ILSVRC2016 val, ResNet-50 on SR imagesTop-1 error (%): 31.1 -> 30.9Improved
add image GAN and perceptual loss to MSE-trained generatorSRFeatM · ILSVRC2016 val, ResNet-50 on SR imagesTop-5 error (%): 20.1 -> 11.9Improved
use 128 filters instead of 64 in GAN-trained generator (ablation)SRFeatIF · ILSVRC2016 val, ResNet-50 on SR imagesTop-5 error (%): 11.8 -> 11.0Improved
use 128 filters instead of 64 in GAN-trained generator (ablation)SRFeatIF · ILSVRC2016 val, ResNet-50 on SR imagesTop-1 error (%): 33.0 -> 30.9Improved
add 1x1 convolution to long-range skip connections (ablation)SRFeatM · Set5 x4PSNR (dB): 32.05 -> 32.27Improved
add 1x1 convolution to long-range skip connections (ablation)SRFeatM · Set14 x4PSNR (dB): 28.59 -> 28.71Improved
add 1x1 convolution to long-range skip connections (ablation)SRFeatM · BSD100 x4PSNR (dB): 27.56 -> 27.64Improved
add long-range skip connections (with 1x1 conv) (ablation)SRFeatM · Set5 x4PSNR (dB): 32.22 -> 32.27Improved
add long-range skip connections (with 1x1 conv) (ablation)SRFeatM · Set14 x4PSNR (dB): 28.71 -> 28.71No clear effect
add long-range skip connections (with 1x1 conv) (ablation)SRFeatM · BSD100 x4PSNR (dB): 27.63 -> 27.64Improved
double feature channels from 64 to 128 (ablation)SRFeatM-64 · Set5 x4PSNR (dB): 32.14 -> 32.27Improved

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