atlas

Research map / Image generation / Super-resolution

GCFSR: A Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors

CVPR 2022 · Image generation › Super-resolution · approach: Perceptual and real-world SR · 82 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 GCFSR instead of GAN-prior-based alternativesFace SR · CelebA-HQ 16×, 32×, and 64× SRPSNR: 27.07 -> 27.17; 24.81 -> 24.95; 22.26 -> 22.39Helped
Use GCFSR instead of GAN-prior-based alternativesFace SR · CelebA-HQ 16× and 32× SRFID: 29.99 -> 30.48; 46.00 -> 43.34Mixed
Train GCFSR with adversarial loss only, without pixel-wise or perceptual lossGCFSR · CelebA-HQ 4× and 8× SRLPIPS: 0.1409 -> 0.1210; 0.1736 -> 0.1704Helped
Add style modulation to generate realistic face details (ablation)GCFSR · CelebA-HQ 16×, 32×, and 64× SRperceptual qualityHelped
Add L1 and perceptual losses to adversarial trainingGCFSR · Large-factor face SR (16×, 32×, 64×)SR performanceHelped

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