AI Paper Atlas

Research map / Image generation / Super-resolution

From Face to Natural Image: Learning Real Degradation for Blind Image Super-Resolution

Xiaoming Li, Chaofeng Chen, Xianhui Lin, Wangmeng Zuo, Lei Zhang

ECCV 2022 · Image generation › Super-resolution · approach: Real-world super-resolution · 21 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 the disentanglement loss to ReDegNet training (ablation)F2N-ESRGAN · RealLQSetNIQE: 6.27 -> 4.93Improved
add the disentanglement loss to ReDegNet training (ablation)F2N-ESRGAN · RealSR-CanonLPIPS: .463 -> .362Improved
add the disentanglement loss to ReDegNet training (ablation)F2N-ESRGAN · RealSR-CanonPSNR: 24.63 -> 25.57Improved
use paired LQ/HQ face images (supervised) instead of unpaired data (ablation)F2N-ESRGAN · RealLQSetNIQE: 5.93 -> 4.93Improved
use paired LQ/HQ face images (supervised) instead of unpaired data (ablation)F2N-ESRGAN · DRealSRLPIPS: .404 -> .373Improved
use paired LQ/HQ face images (supervised) instead of unpaired data (ablation)F2N-ESRGAN · RealSRSetNIQE: 5.81 -> 4.85Improved
learned face-derived degradation (F2N-ESRGAN) versus handcrafted degradation (Real-ESRGAN)ESRGAN · RealLQSetNIQE: 5.24 -> 4.93Improved
learned face-derived degradation (F2N-ESRGAN) versus RealSR degradationESRGAN · RealSRSetNIQE: 4.82 -> 4.85Hurt
learned face-derived degradation (F2N-ESRGAN) versus BSRGANESRGAN · RealSR-CanonPSNR: 25.61 -> 25.57No clear effect
learned face-derived degradation (F2N-ESRGAN) versus BSRGANESRGAN · DRealSRLPIPS: .380 -> .373Improved

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