AI Paper Atlas

Research map / 3D vision / Face and shape

RigNeRF: Fully Controllable Neural 3D Portraits

CVPR 2022 · 3D vision › Face and shape · approach: Face reflectance and relightable rendering · 129 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
Replace pose and expression parameters as deformation-MLP inputs with the 3DMM deformation (ablation)RigNeRF · Held-out test setLPIPS: 0.183 -> 0.161Helped
Replace pose and expression parameters as deformation-MLP inputs with the 3DMM deformation (ablation)RigNeRF · Held-out test setFaceMSE: 1.5e-4 -> 1.3e-4Helped
Replace pose and expression parameters as deformation-MLP inputs with the 3DMM deformation (ablation)RigNeRF · Held-out test setPSNR: 28.5 -> 29.0Helped
Add 3DMM-conditioned appearance (ablation)RigNeRF with 3DMM-deformation input · Held-out test setLPIPS: 0.161 -> 0.119Helped
Add 3DMM-conditioned appearance (ablation)RigNeRF with 3DMM-deformation input · Held-out test setFaceMSE: 1.3e-4 -> 9.8e-5Helped
Add 3DMM-conditioned appearance (ablation)RigNeRF with 3DMM-deformation input · Held-out test setPSNR: 29.0 -> 29.45Helped

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