Overview Statistic: PDF-Downloads (blue) and Frontdoor-Views (gray)

Fully Automated and Highly Accurate Dense Correspondence for Facial Surfaces

  • We present a novel framework for fully automated and highly accurate determination of facial landmarks and dense correspondence, e.g. a topologically identical mesh of arbitrary resolution, across the entire surface of 3D face models. For robustness and reliability of the proposed approach, we are combining 2D landmark detectors and 3D statistical shape priors with a variational matching method. Instead of matching faces in the spatial domain only, we employ image registration to align the 2D parametrization of the facial surface to a planar template we call the Unified Facial Parameter Domain (ufpd). This allows us to simultaneously match salient photometric and geometric facial features using robust image similarity measures while reasonably constraining geometric distortion in regions with less significant features. We demonstrate the accuracy of the dense correspondence established by our framework on the BU3DFE database with 2500 facial surfaces and show, that our framework outperforms current state-of-the-art methods with respect to the fully automated location of facial landmarks.

Download full text files

Export metadata

Metadaten
Author:Carl Martin GreweORCiD, Stefan ZachowORCiD
Document Type:In Proceedings
Parent Title (German):Computer Vision – ECCV 2016 Workshops
Volume:9914
First Page:552
Last Page:568
Publisher:Springer International Publishing
Fulltext Url:https://opus4.kobv.de/opus4-zib/files/6076/grewezachow2016-dense_correspondence.pdf
Year of first publication:2016
Page Number:16
DOI:https://doi.org/10.1007/978-3-319-48881-3_38
Accept ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.