AI Paper Atlas

Research map / Image generation / GANs

In-Domain GAN Inversion for Real Image Editing

Jiapeng Zhu, Yujun Shen, Deli Zhao, Bolei Zhou

ECCV 2020 · Image generation › GANs · approach: Large-scale GAN latent analysis · 560 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
train encoder through the generator on real images (domain-guided) instead of latent-space regressionencoder-based inversion · Image reconstruction (Face)FID: 88.48 -> 52.85Improved
use domain-guided encoder as initialization and regularizer for optimizationMSE-based optimization · Image reconstruction (Face)FID: 58.04 -> 42.64Improved
use domain-guided encoder as initialization and regularizer for optimizationMSE-based optimization · Image reconstruction (Tower)FID: 69.16 -> 44.77Improved
use domain-regularized optimization instead of plain MSE optimizationStyleGAN face inversion · Image reconstruction (Face)MSE: 0.026 -> 0.030Hurt
start optimization from the domain-guided encoder outputoptimization-based inversion · Inference speedtime per image: 290s -> 8sImproved
use in-domain inversion instead of MSE-based optimizationStyleGAN · Image interpolation (Face)FID: 112.09 -> 91.18Improved
use in-domain inversion instead of MSE-based optimizationStyleGAN · Image interpolation (Tower)FID: 121.38 -> 57.22Improved
use in-domain inversion instead of MSE-based optimizationStyleGAN · Image manipulation (Face)FID: 83.69 -> 76.43Improved
use in-domain inversion instead of MSE-based optimizationStyleGAN · Image manipulation (Tower)FID: 113 -> 57.92Improved
increase domain regularization weight lambda_dom from 0 to 40 (ablation)domain-regularized optimization · Face reconstruction and manipulationimage qualityMixed

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