3D morphable model fitting from multiple views

Nathan Faggian; Andrew Paplinski; Jamie Sherrah

doi:10.1109/AFGR.2008.4813340

3D morphable model fitting from multiple views

Nathan Faggian, Andrew Paplinski, Jamie Sherrah

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

19 Citations (Scopus)

Abstract

This paper presents a method to fit a 3D Morphable Model to a sequence of extracted facial features. The approach is a direct extension of a single view method. The novelty is presented as a new mathematical derivation of the same method but for multiple views where identity and pose are known. The new fitting method exploits point-to-model correspondences and can deal with occlusion since features are not required to correspond across views. The mathematics is explained in detail and the methods single tunable parameter is empirically determined using a database of scanned heads.

Original language	English
Title of host publication	2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008
DOIs	https://doi.org/10.1109/AFGR.2008.4813340
Publication status	Published - 1 Dec 2008
Event	2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008 - Amsterdam, Netherlands Duration: 17 Sept 2008 → 19 Sept 2008

Conference

Conference	2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008
Country/Territory	Netherlands
City	Amsterdam
Period	17/09/08 → 19/09/08

Access to Document

10.1109/AFGR.2008.4813340

Cite this

@inproceedings{cfabeb1c77124365b5cede1641a6d5b0,

title = "3D morphable model fitting from multiple views",

abstract = "This paper presents a method to fit a 3D Morphable Model to a sequence of extracted facial features. The approach is a direct extension of a single view method. The novelty is presented as a new mathematical derivation of the same method but for multiple views where identity and pose are known. The new fitting method exploits point-to-model correspondences and can deal with occlusion since features are not required to correspond across views. The mathematics is explained in detail and the methods single tunable parameter is empirically determined using a database of scanned heads.",

author = "Nathan Faggian and Andrew Paplinski and Jamie Sherrah",

year = "2008",

month = dec,

day = "1",

doi = "10.1109/AFGR.2008.4813340",

language = "English",

isbn = "9781424421541",

booktitle = "2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008",

note = "2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008 ; Conference date: 17-09-2008 Through 19-09-2008",

}

TY - GEN

T1 - 3D morphable model fitting from multiple views

AU - Faggian, Nathan

AU - Paplinski, Andrew

AU - Sherrah, Jamie

PY - 2008/12/1

Y1 - 2008/12/1

N2 - This paper presents a method to fit a 3D Morphable Model to a sequence of extracted facial features. The approach is a direct extension of a single view method. The novelty is presented as a new mathematical derivation of the same method but for multiple views where identity and pose are known. The new fitting method exploits point-to-model correspondences and can deal with occlusion since features are not required to correspond across views. The mathematics is explained in detail and the methods single tunable parameter is empirically determined using a database of scanned heads.

AB - This paper presents a method to fit a 3D Morphable Model to a sequence of extracted facial features. The approach is a direct extension of a single view method. The novelty is presented as a new mathematical derivation of the same method but for multiple views where identity and pose are known. The new fitting method exploits point-to-model correspondences and can deal with occlusion since features are not required to correspond across views. The mathematics is explained in detail and the methods single tunable parameter is empirically determined using a database of scanned heads.

UR - http://www.scopus.com/inward/record.url?scp=67650699824&partnerID=8YFLogxK

U2 - 10.1109/AFGR.2008.4813340

DO - 10.1109/AFGR.2008.4813340

M3 - Conference Paper

AN - SCOPUS:67650699824

SN - 9781424421541

BT - 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008

T2 - 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008

Y2 - 17 September 2008 through 19 September 2008

ER -

3D morphable model fitting from multiple views

Abstract

Conference

Access to Document

Other files and links

Cite this