English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 Local TagsRelease HistoryDetailsSummary
  Appealing Avatars from 3D Body Scans: Perceptual Effects of Stylization

Fleming, R., Mohler, B., Romero, J., Black, M., & Breidt, M. (2017). Appealing Avatars from 3D Body Scans: Perceptual Effects of Stylization. In J. Braz, N. Magnenat-Thalmann, P. Richard, L. Linsen, A. Telea, S. Battiato, et al. (Eds.), Computer Vision, Imaging and Computer Graphics: Theory and Applications - 11th International Joint Conference, VISIGRAPP 2016 (pp. 175-196). Cham, Switzerland: Springer International Publishing.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/21.11116/0000-0000-C397-9 Version Permalink: https://hdl.handle.net/21.11116/0000-0003-FE97-5
Genre: Conference Paper

Files

show Files

Locators

show
hide
Locator:
Link (Publisher version)
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Fleming, R1, 2, 3, Author           
Mohler, BJ1, 3, Author           
Romero, J, Author           
Black, MJ4, Author           
Breidt, M2, 3, Author           
Affiliations:
1Research Group Space and Body Perception, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_2528693              
2Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497797              
3Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794              
4Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497638              

Content

show
hide
Free keywords: -
 Abstract: Advances in 3D scanning technology allow us to create realistic virtual avatars from full body 3D scan data.
However, negative reactions to some realistic computer generated humans suggest that this approach might
not always provide the most appealing results. Using styles derived from existing popular character designs,
we present a novel automatic stylization technique for body shape and colour information based on a statistical
3D model of human bodies. We investigate whether such stylized body shapes result in increased perceived
appeal with two different experiments: One focuses on body shape alone, the other investigates the additional
role of surface colour and lighting. Our results consistently show that the most appealing avatar is a partially stylized one. Importantly, avatars with high stylization or no stylization at all were rated to have the least appeal. The inclusion of colour information and improvements to render quality had no significant effect on
the overall perceived appeal of the avatars, and we observe that the body shape primarily drives the change in appeal ratings. For body scans with colour information, we found that a partially stylized avatar was most effective, increasing average appeal ratings by approximately 34.

Details

show
hide
Language(s):
 Dates: 2016-022017-08
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1007/978-3-319-64870-5_9
BibTex Citekey: FlemingMRBB2016
 Degree: -

Event

show
hide
Title: 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2016)
Place of Event: Roma, Italy
Start-/End Date: 2016-02-27 - 2016-02-29

Legal Case

show

Project information

show

Source 1

show
hide
Title: Computer Vision, Imaging and Computer Graphics: Theory and Applications - 11th International Joint Conference, VISIGRAPP 2016
Source Genre: Proceedings
 Creator(s):
Braz, J, Editor
Magnenat-Thalmann, N, Editor
Richard, P, Editor
Linsen, L, Editor
Telea, A, Editor
Battiato, S, Editor
Imai, F, Editor
Affiliations:
-
Publ. Info: Cham, Switzerland : Springer International Publishing
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 175 - 196 Identifier: ISBN: 978-3-319-64869-9

Source 2

show
hide
Title: Communications in Computer and Information Science
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 693 Sequence Number: - Start / End Page: - Identifier: -