AI Paper Atlas

Research map / 3D vision / Face and shape

Dense 3D Face Correspondence

Syed Zulqarnain Gilani, Ajmal Saeed Mian, Faisal Shafait B, Ian D. Reid

TPAMI 2017 · 3D vision › Face and shape · approach: 3D morphable face model regression · 89 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
add organising faces into a graph (ablation)K3DM dense correspondence · Synthetic faces (2,246 vertices)mean localization error (mm): 2.16 -> 1.28Improved
add keypoint detection (ablation)K3DM dense correspondence · Synthetic faces (2,246 vertices)mean localization error (mm): 3.06 -> 1.28Improved
add feature matching (ablation)K3DM dense correspondence · Synthetic faces (2,246 vertices)mean localization error (mm): 3.61 -> 1.28Improved
add keypoint detection and feature matching together (ablation)K3DM dense correspondence · Synthetic faces (2,246 vertices)mean localization error (mm): 4.78 -> 1.28Improved
add selecting best matches in each iteration (ablation)K3DM dense correspondence · Synthetic faces (2,246 vertices)mean localization error (mm): 2.61 -> 1.28Improved
use NICP variant for densification instead of level-set geodesic curvesK3DM · Synthetic facesmean localization error (mm): 1.28 -> 1.30No clear effect
use K3DM_FR instead of cross-domain K3DM_BO on FRGCv2 landmarksK3DM · FRGCv2 landmark localizationmean landmark error (mm): 3.8 -> 2.9Improved
use K3DM_BO instead of BFM for Bosphorus landmarksBFM · Bosphorus landmark localization (all)mean landmark error (mm): 4.48 -> 3.70Improved
use K3DM_BU instead of BFM for cross-domain FRGCv2 recognitionBFM · FRGCv2 rank-1 (cross domain)rank-1 accuracy (%): 76.4% -> 80.5%Improved
use K3DM_BO instead of BFM for cross-domain FRGCv2 recognitionBFM · FRGCv2 rank-1 (cross domain)rank-1 accuracy (%): 76.4% -> 77.1%Improved
use K3DM_BU instead of BFM for cross-domain Bosphorus recognitionBFM · Bosphorus rank-1 (cross domain)rank-1 accuracy (%): 82.7% -> 90.7%Improved
use K3DM_FR for UND45LR rank-1 recognition vs Smeets et al.K3DM_FR · UND45LRrank-1 accuracy (%): 98.3% vs 95.8%Hurt

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