Generalization to Novel Views from a Single Face Image

Vetter, T; Blanz, V

doi:10.1007/978-3-642-72201-1_16

Local TagsRelease HistoryDetailsSummary

Generalization to Novel Views from a Single Face Image

Vetter, T., & Blanz, V. (1998). Generalization to Novel Views from a Single Face Image. In J. Wechsler, J. Phillips, V. Bruce, F. Fogelman Soulié, & T. Huang (Eds.), Face Recognition: From Theory to Applications (pp. 310-326). Berlin, Germany: Springer.

Item is Released

show all hide all

Basic

show hide

Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-E9BC-8 Version Permalink: https://hdl.handle.net/21.11116/0000-0005-DCC7-3

Genre: Conference Paper

Files

show Files

Locators

show

hide

Locator:
https://link.springer.com/content/pdf/10.1007%2F978-3-642-72201-1_16.pdf (Publisher version) Open Access status unknown

Description:
-

OA-Status:

Creators

show

hide

Creators:
Vetter, T^{1, 2}, Author
Blanz, V^{1, 2}, Author

Affiliations:
1Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497797
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794

Content

show

hide

Free keywords: -

Abstract: When only a single image of a face is available, can we generate new images of the face across changes in viewpoint or illumination? The approach presented in this paper acquires its knowledge about possible image changes from other faces and transfers this prior knowledge to a novel face image. In previous work we introduced the concept of linear object classes (Vetter and Poggio, 1997; Vetter, 1997): In an image based approach, a flexible image model of faces was used to synthesize new images of a face when only a single 2D image of that face is available.

In this paper we describe a new general flexible face model which is now “learned” from examples of individual 3D-face data (Cyberware-scans). In an analysis-by-synthesis loop the flexible 3D model is matched to the novel face image. Variation of the model parameters, similar to multidimensional morphing, allows for generating new images of the face where viewpoint, illumination or even the expression is changed.

The key problem for generating a flexible face model is the computation of dense correspondence between all given example faces. A new correspondence algorithm is described, which is a generalization of existing algorithms for optic flow computation to 3D-face data.

Details

show

hide

Language(s):

Dates: Date issued: 1998

Publication Status: Issued

Pages: -

Publishing info: -

Table of Contents: -

Rev. Type: -

Identifiers: BibTex Citekey: VetterB1997
DOI: 10.1007/978-3-642-72201-1_16

Degree: -

Event

show

hide

Title: NATO Advanced Study Institute on Face Recognition: From Theory to Applications 1997

Place of Event: Stirling, UK

Start-/End Date: 1997-06-23 - 1997-07-04

Legal Case

show

Project information

show

Source 1

show

hide

Title: Face Recognition: From Theory to Applications

Source Genre: Proceedings

Creator(s):
Wechsler, J, Editor
Phillips, JP, Editor
Bruce, V, Editor
Fogelman Soulié, F, Editor
Huang, TS, Editor

Affiliations:
-

Publ. Info: Berlin, Germany : Springer

Pages: 636 Volume / Issue: - Sequence Number: - Start / End Page: 310 - 326 Identifier: ISBN: 978-3-642-72203-5

Source 2

show

hide

Title: NATO ASI Series

Source Genre: Series

Creator(s):

Affiliations:

Publ. Info: -

Pages: - Volume / Issue: 163 Sequence Number: - Start / End Page: - Identifier: -