atlas

Research map / 3D vision / Face and shape

[Re] Lifting 2D StyleGAN for 3D-Aware Face Generation

NeurIPS 2022 · 3D vision › Face and shape · approach: Face reflectance and relightable rendering

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
Add symmetric reconstruction loss (ablation)LiftedGAN · StyleGAN2-generated facesDepth error: 0.623 -> 0.435Helped
Add symmetric reconstruction loss (ablation)LiftedGAN · StyleGAN2-generated facesYaw error: 9.37 -> 1.86Helped
Add perturbation loss (ablation)LiftedGAN · StyleGAN2-generated facesDepth error: 0.548 -> 0.435Helped
Add perturbation loss (ablation)LiftedGAN · StyleGAN2-generated facesFID: 21.30 -> 29.81Hurt
Add identity regularization loss (ablation)LiftedGAN · StyleGAN2-generated facesDepth error: 0.498 -> 0.435Helped
Add identity regularization loss (ablation)LiftedGAN · StyleGAN2-generated facesFID: 30.63 -> 29.81Hurt
Add albedo consistency loss (ablation)LiftedGAN · StyleGAN2-generated facesDepth error: 0.467 -> 0.435Helped
Add albedo consistency loss (ablation)LiftedGAN · StyleGAN2-generated facesFID: 27.34 -> 29.81Hurt

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