AI Paper Atlas

Research map / 3D vision / Face and shape

A Sparse and Locally Coherent Morphable Face Model for Dense Semantic Correspondence Across Heterogeneous 3D Faces

Claudio Ferrari, Stefano Berretti, Pietro Pala, Alberto Del Bimbo

TPAMI 2021 · 3D vision › Face and shape · approach: 3D morphable face model regression · 28 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
replace nearest-neighbor correspondence with mean-point association and outlier rejection (ablation)NRF with SLC · FRGCv2.0, Bosphorus, FaceWarehouselandmark errorImproved
use SLC components instead of PCA in NRF (ablation)NRF · FaceWarehouse landmark localizationavg landmark error (mm): 4.6 -> 4.1Improved
use SLC components instead of DL in NRF (ablation)NRF · FaceWarehouse landmark localizationavg landmark error (mm): 4.3 -> 4.1Improved
use SLC components instead of PCA in NRF (ablation)NRF · FRGCv2.0 landmark localizationavg landmark error (mm): 3.0 -> 2.8Improved
use SLC components instead of DL in NRF (ablation)NRF · Bosphorus landmark localization (Expression subset)avg landmark error (mm): 3.0 -> 3.1No clear effect
register with NRF+SLC instead of NICP before building PCA model (ablation)HLS-3DMM · HLS-3DMM compactness (9,927 scans)components for 90% variance: 114 -> 43Improved
use SLC components instead of PCA in registration for compactness (ablation)HLS-3DMM · HLS-3DMM compactness (9,927 scans)components for 90% variance: 47 -> 43Improved
reduce CoMA training set to 360 scans (2%) (ablation)SLC · CoMA (identity split, k=512)vertices with error below 1mm (%): 92% -> 79%Hurt
reduce CoMA training set to 360 scans (2%) (ablation)Neural3DMM · CoMA (identity split, k=512)vertices with error below 1mm (%): drops down to 0%Hurt
increase number of components k from 64 to 512 (ablation)SLC · SLC component sparsityzero entries in C (%): 84.4% -> 96.3%Mixed
remove l2 regularization from SLC learning (l1 only) (ablation)SLC components · component visualizationdeformation smoothnessHurt
use SLC instead of PCA with small k (up to 64 components) (ablation)CoMA identity split · CoMA identity splitreconstruction errorHurt

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