AI Paper Atlas

Research map / Image generation / Super-resolution

EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis

Mehdi S. M. Sajjadi, Bernhard Scholkopf, Michael Hirsch

ICCV 2017 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 1,106 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 adversarial loss to MSE training (ablation)ENet-E · Set5 (4x)PSNR: 31.74 -> 28.15Hurt
add adversarial loss to perceptual loss (ablation)ENet-P · Set14 (4x)PSNR: 25.64 -> 24.93Hurt
add texture matching loss to perceptual plus adversarial loss (ablation)ENet-PA · Set5 (4x)PSNR: 27.20 -> 28.56Improved
add texture matching loss to perceptual plus adversarial loss (ablation)ENet-PA · Urban100 (4x)PSNR: 22.51 -> 23.54Improved
add texture loss to MSE plus adversarial loss (ablation)ENet-EA · BSD100 (4x)PSNR: 25.71 -> 25.97Improved
replace MSE with perceptual loss (ablation)ENet-E · Set5 (4x)PSNR: 31.74 -> 28.28Hurt
add adversarial loss to perceptual loss (ablation)ENet-P · ImageNet ResNet-50 recognitiontop-1 error: 0.449 -> 0.399Improved
add adversarial loss to MSE training (ablation)ENet-E · ImageNet ResNet-50 recognitiontop-1 error: 0.449 -> 0.407Improved
train with perceptual+adversarial+texture loss instead of MSE (ablation)ENet-E · ImageNet ResNet-50 recognitionconfidence: 0.754 -> 0.797Improved
use ENet-PAT instead of ENet-E in user study (ablation)ENet-E · ImageNet user studypreference: 91.0%Improved
train with MSE loss instead of bicubic baselineBicubic · Set5 (4x)PSNR: 28.42 -> 31.74Improved
use ENet-E instead of VDSRVDSR · Set5 (4x)PSNR: 31.35 -> 31.74Improved

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