atlas

Research map / 3D vision / Face and shape

GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction

CVPR 2019 · 3D vision › Face and shape · approach: Face reflectance and relightable rendering · 332 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
use GANFIT instead of Genova et al.3D face shape reconstruction · MICC Cooperativepoint-to-plane distance (mm): 1.50 -> 0.95Helped
use GANFIT instead of Genova et al.3D face shape reconstruction · MICC Indoorpoint-to-plane distance (mm): 1.50 -> 0.94Helped
use GANFIT instead of Genova et al.3D face shape reconstruction · MICC Outdoorpoint-to-plane distance (mm): 1.48 -> 0.94Helped
add identity loss terms (ablation)GANFIT · 3D face reconstructionidentity preservationHelped
add identity features (ablation)GANFIT · 3D face reconstructionreconstruction qualityHelped
add pixel loss (ablation)GANFIT · 3D face reconstructionalbedo and illumination qualityHelped
use GAN texture prior instead of PCA-based texture (ablation)GANFIT · 3D face reconstructiontexture qualityHelped

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