AI Paper Atlas

Research map / 3D vision / Face and shape

Learning Dense Facial Correspondences in Unconstrained Images

Ronald Yu, Shunsuke Saito, Haoxiang Li, Duygu Ceylan, Hao Li

ICCV 2017 · 3D vision › Face and shape · approach: 3D morphable face model regression · 78 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
use dense-correspondence network instead of Zhu et al. cascaded CNN regression3DMM face fitting · AFLW2000 visible inner landmarks (all images)NMS error: 4.60 -> 3.58Improved
use dense-correspondence network instead of Zhu et al.3DMM face fitting · AFLW2000 68 landmarks (yaw 60-90)NMS error: 7.93 -> 9.56Hurt
use dense-correspondence network instead of SDM3DMM face fitting · AFLW2000 68 landmarks (yaw 30-60)NMS error: 4.94 -> 6.06Hurt
use dense-correspondence network instead of SDM3DMM face fitting · AFLW2000 68 landmarks (yaw 0-30)NMS error: 3.67 -> 3.62No clear effect
use dense-correspondence network instead of Zhu et al.3DMM face fitting · AFLW visible landmarks (yaw 0-30)NMS error: 5.00 -> 5.94Hurt
use dense-correspondence network instead of Zhu et al.3DMM face fitting · AFLW visible landmarks (yaw >60)NMS error: 6.74 -> 7.96Hurt
use dense-correspondence network instead of Jourabloo et al.3DMM face fitting · AFLW-PIFA 21 landmarksNMS error: 4.72 -> 5.42Hurt
replace iterative cascaded regression (Zhu et al.) with single-pass flow networkface alignment · Runtime large-pose alignmentms per image: 75.7 -> 9.35Improved
replace Jourabloo et al. with single-pass flow networkface alignment · Runtime large-pose alignmentms per image: 1666 -> 9.35Improved
fine-tune the synthetic-trained network on real 300W-LP photographs (ablation)dense correspondence network · real imagesqualitativeImproved

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