AI Paper Atlas

Research map / 3D vision / Face and shape

Building 3D Generative Models from Minimal Data

Skylar Sutherland, Bernhard Egger, Joshua B. Tenenbaum

IJCV 2023 · 3D vision › Face and shape · approach: 3D morphable face model regression · 10 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
combine RGB-space and physical-space distance in the albedo kernel (vs RGB only) (ablation)single-scan 3DMM · Multi-PIE 45 deg yawaccuracy: 28.9 -> 54.2Improved
combine RGB-space and physical-space distance in the albedo kernel (vs XYZ only) (ablation)single-scan 3DMM · Multi-PIE 45 deg yawaccuracy: 35.7 -> 54.2Improved
add bilateral symmetry and color correlation kernels (ablation)standard-full 3DMM · Multi-PIE 45 deg yawaccuracy: 54.2 -> 72.3Improved
add bilateral symmetry and color correlation kernels (ablation)standard-full 3DMM · Multi-PIE 15 deg yawaccuracy: 84.7 -> 93.2Improved
add symmetry on top of color correlation (ablation)correlated-full 3DMM · Multi-PIE 45 deg yawaccuracy: 66.7 -> 72.3Improved
add symmetry on top of color correlation (ablation)correlated-full 3DMM · Multi-PIE 30 deg yawaccuracy: 87.1 -> 85.9No clear effect
use mean of Basel Face Model 2019 as template instead of a single individual scansymmetric 3DMM · Multi-PIE 45 deg yawaccuracy: 49.8 -> 72.3Improved
replace 10-scan PCA with 10-scan KDE mixture of single-scan 3DMMs10-scan 3DMM · Multi-PIE 45 deg yawaccuracy: 42.2 -> 71.5Improved
replace 10-scan PCA with 10-scan KDE mixture of single-scan 3DMMs10-scan 3DMM · Multi-PIE 15 deg yawaccuracy: 86.0 -> 94.0Improved
add albedo information to MCMC registration (vs shape only) (ablation)single-scan 3DMM registration · registration of 10 scansshape error: slightly increases shape errorMixed
learn 3DMM from 2D images by wake-sleep iterationsstandard-full / symmetric-full 3DMM · Multi-PIE face recognitionaccuracyHurt

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