AI Paper Atlas

Research map / 3D vision / Face and shape

Boosting Local Shape Matching for Dense 3D Face Correspondence

Zhenfeng Fan, Xiyuan Hu, Chen Chen, Silong Peng

CVPR 2019 · 3D vision › Face and shape · approach: 3D morphable face model regression · 13 citations (OpenAlex)

Check 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 the proposed dense correspondence method rather than the strongest listed baselineFRGC v2.0 outer eye corner (Ex) · FRGC v2.0landmark localization error (mm; mean): 2.5 -> 2.1Improved
Use the proposed dense correspondence method rather than the strongest listed baselineFRGC v2.0 inner eye corner (En) · FRGC v2.0landmark localization error (mm; mean): 2.4 -> 1.9Improved
Use the proposed dense correspondence method rather than the strongest listed baselineFRGC v2.0 nose bridge saddle (N) · FRGC v2.0landmark localization error (mm; mean): 2.4 -> 2.4No clear effect
Use the proposed dense correspondence method rather than the strongest listed baselineFRGC v2.0 nose tip (Prn) · FRGC v2.0landmark localization error (mm; mean): 2.1 -> 1.8Improved
Use the proposed dense correspondence method rather than the strongest listed baselineFRGC v2.0 nasal base (Sn) · FRGC v2.0landmark localization error (mm; mean): 2.7 -> 1.8Improved
Use the proposed dense correspondence method rather than the strongest listed baselineFRGC v2.0 nose corner (Ac) · FRGC v2.0landmark localization error (mm; mean): 2.6 -> 1.9Improved
Use the proposed dense correspondence method rather than the strongest listed baselineFRGC v2.0 mouth corner (Ch) · FRGC v2.0landmark localization error (mm; mean): 2.5 -> 2.8Hurt
Use the proposed dense correspondence method rather than the strongest listed baselineFRGC v2.0 upper lip midpoint (Ls) · FRGC v2.0landmark localization error (mm; mean): 2.4 -> 2.0Improved
Use the proposed dense correspondence method rather than the strongest listed baselineFRGC v2.0 lower lip midpoint (Li) · FRGC v2.0landmark localization error (mm; mean): 3.5 -> 4.3Hurt
Fit correspondence with the proposed method instead of NICP or the BFM modelPCA model of 200 corresponded samples · Collected high-resolution face databaseprincipal components needed to explain 99% energy: 59(63) -> 43Improved

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