Creating Ultra Dense Point Correspondence Over the Entire Human Head

Rasmus Reinhold Paulsen; Kasper Korsholm Marstal; Søren  Laugesen; Stine Harder

doi:10.1007/978-3-319-59129-2 37

Creating Ultra Dense Point Correspondence Over the Entire Human Head

Rasmus Reinhold Paulsen, Kasper Korsholm Marstal, Søren Laugesen, Stine Harder

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

639 Downloads (Pure)

Abstract

While the acquisition and analysis of 3D faces has been an active area of research for decades, it is still a complex and demanding task to accurately model the entire head and ears. Having accurate models would for example enable virtual design of hearing devices. In this paper, we describe a complete framework for surface registration of complete human heads where the result is point correspondence with a very high number of points. The method is based on a volumetric and multi-scale non-rigid registration of signed distance fields. The method is evaluated on a set of 30 human heads and the results are convincing. The output can for example be used to compute statistical shape models. The accuracy of predicted anatomical landmarks is on the level of experienced human operators.

Original language	English
Title of host publication	Lecture Notes in Computer Science : Image Analysis
Volume	10270
Publisher	Springer
Publication date	2017
Pages	438-447
ISBN (Print)	978-3-319-59128-5
ISBN (Electronic)	978-3-319-59129-2
DOIs	https://doi.org/10.1007/978-3-319-59129-2 37
Publication status	Published - 2017
Event	20th Scandinavian Conference on Image Analysis - Tromsø, Norway Duration: 12 Jun 2017 → 14 Jun 2017 Conference number: 20 https://link.springer.com/book/10.1007/978-3-319-59126-1

Conference

Conference	20th Scandinavian Conference on Image Analysis
Number	20
Country/Territory	Norway
City	Tromsø
Period	12/06/2017 → 14/06/2017
Internet address	https://link.springer.com/book/10.1007/978-3-319-59126-1

Series	Lecture Notes in Computer Science
ISSN	0302-9743

Keywords

Surface registration
Signed distance field
Human head modelling

Access to Document

10.1007/978-3-319-59129-2 37

FullHeads finalAccepted author manuscript, 9.51 MB

OpenUrl availability

Full text

Cite this

@inproceedings{ab8471ab6a77462d8aa9ba528cbddd95,

title = "Creating Ultra Dense Point Correspondence Over the Entire Human Head",

abstract = "While the acquisition and analysis of 3D faces has been an active area of research for decades, it is still a complex and demanding task to accurately model the entire head and ears. Having accurate models would for example enable virtual design of hearing devices. In this paper, we describe a complete framework for surface registration of complete human heads where the result is point correspondence with a very high number of points. The method is based on a volumetric and multi-scale non-rigid registration of signed distance fields. The method is evaluated on a set of 30 human heads and the results are convincing. The output can for example be used to compute statistical shape models. The accuracy of predicted anatomical landmarks is on the level of experienced human operators.",

keywords = "Surface registration, Signed distance field, Human head modelling",

author = "Paulsen, {Rasmus Reinhold} and Marstal, {Kasper Korsholm} and S{\o}ren Laugesen and Stine Harder",

year = "2017",

doi = "10.1007/978-3-319-59129-2 37",

language = "English",

isbn = "978-3-319-59128-5",

volume = "10270",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "438--447",

booktitle = "Lecture Notes in Computer Science",

note = "20th Scandinavian Conference on Image Analysis, SCIA 2017 ; Conference date: 12-06-2017 Through 14-06-2017",

url = "https://link.springer.com/book/10.1007/978-3-319-59126-1",

}

Paulsen, RR, Marstal, KK, Laugesen, S & Harder, S 2017, Creating Ultra Dense Point Correspondence Over the Entire Human Head. in Lecture Notes in Computer Science: Image Analysis. vol. 10270, Springer, Lecture Notes in Computer Science, pp. 438-447, 20th Scandinavian Conference on Image Analysis, Tromsø, Norway, 12/06/2017. https://doi.org/10.1007/978-3-319-59129-2 37

Creating Ultra Dense Point Correspondence Over the Entire Human Head. / Paulsen, Rasmus Reinhold; Marstal, Kasper Korsholm; Laugesen, Søren et al.
Lecture Notes in Computer Science: Image Analysis. Vol. 10270 Springer, 2017. p. 438-447 (Lecture Notes in Computer Science).

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

TY - GEN

T1 - Creating Ultra Dense Point Correspondence Over the Entire Human Head

AU - Paulsen, Rasmus Reinhold

AU - Marstal, Kasper Korsholm

AU - Laugesen, Søren

AU - Harder, Stine

N1 - Conference code: 20

PY - 2017

Y1 - 2017

N2 - While the acquisition and analysis of 3D faces has been an active area of research for decades, it is still a complex and demanding task to accurately model the entire head and ears. Having accurate models would for example enable virtual design of hearing devices. In this paper, we describe a complete framework for surface registration of complete human heads where the result is point correspondence with a very high number of points. The method is based on a volumetric and multi-scale non-rigid registration of signed distance fields. The method is evaluated on a set of 30 human heads and the results are convincing. The output can for example be used to compute statistical shape models. The accuracy of predicted anatomical landmarks is on the level of experienced human operators.

AB - While the acquisition and analysis of 3D faces has been an active area of research for decades, it is still a complex and demanding task to accurately model the entire head and ears. Having accurate models would for example enable virtual design of hearing devices. In this paper, we describe a complete framework for surface registration of complete human heads where the result is point correspondence with a very high number of points. The method is based on a volumetric and multi-scale non-rigid registration of signed distance fields. The method is evaluated on a set of 30 human heads and the results are convincing. The output can for example be used to compute statistical shape models. The accuracy of predicted anatomical landmarks is on the level of experienced human operators.

KW - Surface registration

KW - Signed distance field

KW - Human head modelling

U2 - 10.1007/978-3-319-59129-2 37

DO - 10.1007/978-3-319-59129-2 37

M3 - Article in proceedings

SN - 978-3-319-59128-5

VL - 10270

T3 - Lecture Notes in Computer Science

SP - 438

EP - 447

BT - Lecture Notes in Computer Science

PB - Springer

T2 - 20th Scandinavian Conference on Image Analysis

Y2 - 12 June 2017 through 14 June 2017

ER -

Creating Ultra Dense Point Correspondence Over the Entire Human Head

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this