AI Paper Atlas

Research map / Image generation / GANs

Latent Transformations via NeuralODEs for GAN-Based Image Editing

Valentin Khrulkov, Leyla Mirvakhabova, Ivan Oseledets, Artem Babenko

ICCV 2021 · Image generation › GANs · approach: Large-scale GAN latent analysis · 8 citations (OpenAlex)

Read the paper

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
use nonlinear Neural ODE flow instead of InterFaceGAN linear shift (attribute control, Q1)Ours(nonlinear) · FFHQhuman preference: +34%Improved
use nonlinear Neural ODE flow instead of InterFaceGAN linear shift (attribute control, Q1)Ours(nonlinear) · Places365human preference: +47%Improved
use nonlinear Neural ODE flow instead of a trainable constant (linear) flow (Q1) (ablation)Ours(nonlinear) · FFHQhuman preference: +10%Improved
use nonlinear Neural ODE flow instead of a trainable constant (linear) flow (Q1) (ablation)Ours(nonlinear) · Places365human preference: +48%Improved
use nonlinear flow instead of IF for identity preservation (Q2)Ours(nonlinear) · Places365human preference: -20%Hurt
use nonlinear flow instead of IF for identity preservation (Q2)Ours(nonlinear) · FFHQhuman preference: +4%Improved
use nonlinear flow instead of linear Neural ODE for identity preservation (Q2) (ablation)Ours(nonlinear) · Places365human preference: +31%Improved
use nonlinear flow instead of linear Neural ODE for identity preservation (Q2) (ablation)Ours(nonlinear) · FFHQhuman preference: +5%Improved
replace the L2 attribute-preservation loss with a FaceNet cosine identity loss (ablation)Ours(nonlinear) · FFHQ (13 attributes)identity preservation preference: 60% vs 40%Improved
increase Neural ODE depth from 1 to 2 (ablation)Ours(nonlinear) · FFHQ / Places365visual qualityNo clear effect
use nonlinear flow for small localized attributes such as Smiling or Bushy_EyebrowsOurs(nonlinear) · FFHQvisual qualityNo clear effect
use nonlinear flow for global content attributesOurs(nonlinear) · FFHQ/Places365Spearman correlation: ~0.41Improved

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