AI Paper Atlas

Research map / Image generation / GANs

Conceptual and Hierarchical Latent Space Decomposition for Face Editing

Savas Ozkan, Mete Ozay, Tom Robinson

ICCV 2023 · Image generation › GANs · approach: Large-scale GAN latent analysis · 5 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
edit through hierarchical, conceptual intermediate latent space Q instead of direct mapping to face parameter space (StyleRig)GAN space controller on StyleGAN2 · StyleFlow dataset, all three editsidentity cosine similarity: 0.923 -> 0.963Improved
use intermediate latent space for editing instead of StyleFlowStyleGAN2 face editing · Edit consistency, illuminationmean absolute error: 0.53 -> 0.35Improved
use intermediate latent space instead of StyleRig on edit precisionStyleGAN2 face editing · Edit precision, posemean absolute error: 0.17 -> 0.11Improved
use intermediate latent space instead of StyleRig on expression precisionStyleGAN2 face editing · Edit precision, expressionmean absolute error: 3.67 -> 3.49Improved
swap Basel face model for FLAME with DECAparameter estimation · face editingqualitative equivalenceNo clear effect

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