atlas

Research map / Image generation / Editing and style transfer

Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation

ICLR 2021 · Image generation › Editing and style transfer · approach: GAN inversion for editing · 6 citations (OpenAlex)

Read the paperCheck 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 the proposed latent-direction method instead of Voynov et al.StyleGAN2 face editing · CelebA-HQ faces, Smile (|ε̂| in (0, .3])change in other attributes: .115 -> .085Helped
Use the proposed latent-direction method instead of Voynov et al.StyleGAN2 face editing · CelebA-HQ faces, Smile (|ε̂| in (0, .3])image identity similarity: .979 -> .995Helped
Train multiple attribute directions jointly rather than one direction at a time (ablation)Proposed method · Face and scene image editingunintended visual changesHelped
Use a local transformation rather than a global direction (ablation)Proposed method on PGGAN · Face attribute editingvisual editing qualityHelped
Use an MLP direction function rather than a linear-layer direction function (ablation)Local transformation on PGGAN · Face attribute editingvisual editing qualityNo clear effect
Train with the full loss rather than the regression loss alone (ablation)MLP local transformation on PGGAN · Face attribute editingtraining stabilityHelped

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