atlas

Research map / 3D vision / Face and shape

StyleRig: Rigging StyleGAN for 3D Control Over Portrait Images

CVPR 2020 · 3D vision › Face and shape · approach: Face reflectance and relightable rendering · 374 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
Condition a latent edit on both the input latent code and target semantic parametersStyleRig · StyleGAN portrait editingedit qualityHelped
Add reconstruction loss to anchor the mapping in the latent space (ablation)StyleRig · StyleGAN portrait editingimage qualityHelped
Add consistency loss to preserve parameters not being edited (ablation)StyleRig · StyleGAN portrait editingparameter consistencyHelped
Train the latent steering network without using the input latent codeStyleGAN portrait editing · StyleGAN portrait editingedit qualityHurt
Use semantic 3D parameters to control a pretrained StyleGANStyleRig · StyleGAN portrait editingsemantic controlHelped
Attempt in-plane rotation control using the learned rigStyleRig · StyleGAN portrait editingrotation controlHurt

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