research-article

Which facial profile do humans expect after seeing a frontal view? a comparison with a linear face model

Authors:

Matthaeus Schumacher,

Volker BlanzAuthors Info & Claims

ACM Transactions on Applied Perception (TAP), Volume 9, Issue 3

Article No.: 11, Pages 1 - 16

https://doi.org/10.1145/2325722.2325724

Published: 02 August 2012 Publication History

Abstract

Manipulated versions of three-dimensional faces that have different profiles, but almost the same appearance in frontal views, provide a novel way to investigate if and how humans use class-specific knowledge to infer depth from images of faces. After seeing a frontal view, participants have to select the profile that matches that view. The profiles are original (ground truth), average, random other, and two solutions computed with a linear face model (3D Morphable Model). One solution is based on 2D vertex positions, the other on pixel colors in the frontal view. The human responses demonstrate that humans neither guess nor just choose the average profile. The results also indicate that humans actually use the information from the front view, and not just rely on the plausibility of the profiles per se. All our findings are perfectly consistent with a correlation-based inference in a linear face model. The results also verify that the 3D reconstructions from our computational algorithms (stimuli 4 and 5) are similar to what humans expect, because they are chosen to be the true profile equally often as the ground-truth profiles. Our experiments shed new light on the mechanisms of human face perception and present a new quality measure for 3D reconstruction algorithms.

References

[1]

Belhumeur, P. N., Kriegman, D. J., and Yuille, A. L. 1999. The bas-relief ambiguity. Int. J. Comput. Vis. 35, 1, 33--44.

Digital Library

[2]

Blanz, V., Mehl, A., Vetter, T., and Seidel, H.-P. 2004. A statistical method for robust 3d surface reconstruction from sparse data. In Proceedings of the 2nd International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT '04), Y. Aloimonos and G. Taubin, Eds., IEEE, 293--300.

Digital Library

[3]

Blanz, V. and Vetter, T. 1999. A Morphable Model for the synthesis of 3d faces. In Proceedings of SIGGRAPH. 187--194.

Digital Library

[4]

Ezzat, T., Geiger, G., and Poggio, T. 2002. Trainable videorealistic speech animation. In Proceedings of SIGGRAPH'02. 388--398.

Digital Library

[5]

Gregory, R. L. 1997. Knowledge in perception and illusion. Phil. Trans. R. Soc. Lond. B 352, 1121--1128.

[6]

Gummersbach, N. and Blanz, V. 2010. A morphing-based analysis of the perceptual distance metric of human faces. In Proceedings of the 7th Symposium on Applied Perception in Graphics and Visualization (APGV). 109--116.

Digital Library

[7]

Hassner, T. and Basri, R. 2006. Example based 3d reconstruction from single 2d images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (Beyond Patches Workshop).

Digital Library

[8]

Hill, H. and Johnston, A. 2007. The hollow-face illusion: Object-Specific knowledge, general assumptions or properties of the stimulus&quest; Percept. 36, 2, 199--223.

[9]

Jiang, F., Blanz, V., and OToole, A. J. 2006. Probing the visual representation of faces with adaptation: A view from the other side of the mean. Psychol. Sci. 17, 493--500.

[10]

Koenderink, J. J., van Doorn, A. J., Kappers, A. M. L., and Todd, J. T. 1997. The visual contour in depth. Percep. Psychophys. 59, 6, 828--838.

[11]

Leopold, D. A., O'Toole, A. J., Vetter, T., and Blanz, V. 2001. Prototype-Referenced shape encoding revealed by high-level aftereffects. Nature Neurosci. 4, 1, 89--94.

[12]

Mallot, H. 2000. Computational Vision: Information Processing in Perception and Visual Behavior. MIT Press, Cambridge, MA.

[13]

OToole, A. J., Edelman, S., and Bülthoff, H. H. 1998. Stimulus-specific effects in face recognition over changes in viewpoint. Visi. Res. 38, 2351--2363.

[14]

OToole, A. J., Vetter, T., Volz, H., and Salter, E. M. 1997. Caricatures of three dimensional human heads: As we get older do we get more distinct&quest; Suppl. Invest. Ophthalmol. Vis. Sci. 38, 4662.

[15]

Saxena, A., Sun, M., and Ng, A. Y. 2008. Make3d: Learning 3-d scene structure from a single still image. IEEE Trans. Pattern Anal. Mach. Intell. 31, 5.

Digital Library

[16]

Troje, N. F. and Bülthoff, H. H. 1996. Face recognition under varying pose: The role of texture and shape. Visi. Res. 36, 1761--1771.

[17]

Valentine, T. 1991. A unified account of the effects of distinctiveness, inversion, and race in face recognition. Q. J. Exp. Psychol. A 43A, 161--204.

[18]

Yuille, A. L. and Kersten, D. 2006. Vision as bayesian inference: Analysis by synthesis&quest; Trends Cogn. Neurosci. 10, 7, 301--308.

Cited By

Bülthoff IBreidt MBülthoff HKersten D(2023)General lighting can overcome accidental viewingi-Perception10.1177/2041669523121560414:6Online publication date: 6-Dec-2023
https://doi.org/10.1177/20416695231215604
Fang YZhang WLiu N(2020)On the Perception Analysis of User Feedback for Interactive Face RetrievalACM Transactions on Applied Perception10.1145/340396417:3(1-20)Online publication date: 3-Aug-2020
https://dl.acm.org/doi/10.1145/3403964
Egger BSmith WTewari AWuhrer SZollhoefer MBeeler TBernard FBolkart TKortylewski ARomdhani STheobalt CBlanz VVetter T(2020)3D Morphable Face Models—Past, Present, and FutureACM Transactions on Graphics10.1145/339520839:5(1-38)Online publication date: 9-Jun-2020
https://dl.acm.org/doi/10.1145/3395208
Show More Cited By

Index Terms

Which facial profile do humans expect after seeing a frontal view? a comparison with a linear face model

Recommendations

Single-view-based 3D facial reconstruction method robust against pose variations

The 3D Morphable Model (3DMM) and the Structure from Motion (SfM) methods are widely used for 3D facial reconstruction from 2D single-view or multiple-view images. However, model-based methods suffer from disadvantages such as high computational costs ...
2D Pose-Invariant Face Recognition Using Single Frontal-View Face Database
Abstract
Personal identification systems that use face recognition work well for test images with frontal view face, but often fail when the input face is a pose view. Most face databases come from picture ID sources such as passports or driver’s licenses. ...
Generating frontal view face image for pose invariant face recognition

Recognizing human faces is one of the most important areas of research in biometrics. However, drastic change of facial poses is a big challenge for its practical application. This paper proposes generating frontal view face image using linear ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Transactions on Applied Perception

ACM Transactions on Applied Perception Volume 9, Issue 3

July 2012

74 pages

ISSN:1544-3558

EISSN:1544-3965

DOI:10.1145/2325722

Issue’s Table of Contents

Copyright © 2012 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 02 August 2012

Accepted: 01 June 2012

Revised: 01 June 2012

Received: 01 May 2012

Published in TAP Volume 9, Issue 3

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed

Funding Sources

INBEKI

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
397
Total Downloads

Downloads (Last 12 months)4
Downloads (Last 6 weeks)0

Reflects downloads up to 16 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Bülthoff IBreidt MBülthoff HKersten D(2023)General lighting can overcome accidental viewingi-Perception10.1177/2041669523121560414:6Online publication date: 6-Dec-2023
https://doi.org/10.1177/20416695231215604
Fang YZhang WLiu N(2020)On the Perception Analysis of User Feedback for Interactive Face RetrievalACM Transactions on Applied Perception10.1145/340396417:3(1-20)Online publication date: 3-Aug-2020
https://dl.acm.org/doi/10.1145/3403964
Egger BSmith WTewari AWuhrer SZollhoefer MBeeler TBernard FBolkart TKortylewski ARomdhani STheobalt CBlanz VVetter T(2020)3D Morphable Face Models—Past, Present, and FutureACM Transactions on Graphics10.1145/339520839:5(1-38)Online publication date: 9-Jun-2020
https://dl.acm.org/doi/10.1145/3395208
Bas ASmith W(2019)What Does 2D Geometric Information Really Tell Us About 3D Face Shape?International Journal of Computer Vision10.1007/s11263-019-01197-xOnline publication date: 25-Jul-2019
https://doi.org/10.1007/s11263-019-01197-x
Schumacher MBlanz V(2015)Exploration of the correlations of attributes and features in faces2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)10.1109/FG.2015.7163124(1-8)Online publication date: May-2015
https://doi.org/10.1109/FG.2015.7163124
Schumacher MPiotraschke MBlanz V(2015)Hallucination of facial details from degraded images using 3D face modelsImage and Vision Computing10.1016/j.imavis.2015.06.00440:C(49-64)Online publication date: 1-Aug-2015
https://dl.acm.org/doi/10.1016/j.imavis.2015.06.004

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Issue’s Table of Contents