research-article

Real or Fake?: human judgments about photographs and computer-generated images of faces

Authors:

Shiqing XinAuthors Info & Claims

SA '12: SIGGRAPH Asia 2012 Technical Briefs

Article No.: 17, Pages 1 - 4

https://doi.org/10.1145/2407746.2407763

Published: 28 November 2012 Publication History

Get Access

Abstract

While efforts to create realistic images have generated break-throughs in computer graphics modeling, there has been little research to date on factors causing people to perceive images as real versus computer-generated (CG). The motivation of the current experiment is to begin investigating such factors. We showed both computer-graphics experts and laypersons real photos and CG images. Photo and CG images were of three types: original, modified to show only intrinsic reflectance components, and modified to show only intrinsic shading components (grayscale). Participants judged whether each image was a real photo or a CG image. Results showed that visual realism depends not only on image properties, but also on cognitive characteristics of viewers. Shading was especially crucial for visual realism. Color was also important. Experts outperformed laypersons, but their advantage was limited to grayscale images. This research at the interface between human cognition and computer vision is a starting point for investigating the factors underlying visual realism.

Supplementary Material

ZIP File (a17-fan.zip)

Supplemental files.

Download
346.01 KB

MP4 File (a17-fan.mp4)

Download
5.57 MB

References

[1]

Bailey, R. A. 2008. Design of comparative experiments. Cambridge University Press.

Google Scholar

[2]

Bruce, V., and Young, A. 2012. Face Perception, 1 ed. Psychology Press.

Google Scholar

[3]

Farid, H., and Bravo, M. J. 2012. Perceptual discrimination of computer generated and photographic faces. Digital Investigation 4, 226--235.

Crossref

Google Scholar

[4]

Grosse, R., Johnson, M. K., Adelson, E. H., and Freeman, W. T. 2009. Ground truth dataset and baseline evaluations for intrinsic image algorithms. In IEEE International Conference on Computer Vision.

Google Scholar

[5]

McNamara, A. 2005. Exploring perceptual equivalence between real and simulated imagery. In Proceedings of the 2nd symposium on APGV, vol. 38.

Digital Library

Google Scholar

[6]

Larkin, M., and Sullivan, C. O. 2011. Perception of simplification artifacts for animated characters. In Proceedings of ACM SIGGRAPH symposium on APGV, 93--100.

Digital Library

Google Scholar

[7]

Meyer, G. W., Rushmere, H. E., Cohen, M. F., Greenberg, D. P., and Torrance, K. E. 1986. An experimental evaluation of computer graphics imagery. ACM Transactions on Graphics 5, 1, 30--50.

Digital Library

Google Scholar

[8]

McDonnell, R., Breidt, B., Bulthoff, H. H. 2012. Render me real? Investigating the effect of render style on the perception of animated virtual humans. ACM Transactions on Graphics.

Digital Library

Google Scholar

[9]

Ng, T. T., and Chang, S. F. 2012. Discrimination of computer synthesized or recaptured images from real images. In Digital Image Forensics, Springer, 275--309.

Google Scholar

[10]

Nisbett, R. E., and Wilson, T. D. 1977. Telling more than we can know. Psychological Review 84, 231--259.

Crossref

Google Scholar

[11]

Wickens, D. T. 2002. Elementary signal detection theory. Oxford University Press.

Google Scholar

Cited By

View all

McElvaney TOsman MMareschal I(2022)Identifying criminals: No biasing effect of criminal context on recalled threatMemory & Cognition10.3758/s13421-021-01268-w50:8(1735-1755)Online publication date: 13-Jan-2022
https://doi.org/10.3758/s13421-021-01268-w
Assaf RKunz STeixeira L(2020)The Presence of the Uncanny Valley Between Animation and CinemaMultidisciplinary Perspectives on New Media Art10.4018/978-1-7998-3669-8.ch005(97-118)Online publication date: 26-Jun-2020
https://doi.org/10.4018/978-1-7998-3669-8.ch005
Salminen JLiu YŞengün SSantos JJung SJansen BPaternò FOliver NConati CSpano LTintarev N(2020)The effect of numerical and textual information on visual engagement and perceptions of AI-driven persona interfacesProceedings of the 25th International Conference on Intelligent User Interfaces10.1145/3377325.3377492(357-368)Online publication date: 17-Mar-2020
https://dl.acm.org/doi/10.1145/3377325.3377492
Show More Cited By

Index Terms

Real or Fake?: human judgments about photographs and computer-generated images of faces
1. Applied computing
  1. Law, social and behavioral sciences
    1. Psychology
2. Computing methodologies
  1. Computer graphics
    1. Image manipulation
      1. Texturing
    2. Rendering
      1. Reflectance modeling

Recommendations

Human Perception of Visual Realism for Photo and Computer-Generated Face Images

Computer-generated (CG) face images are common in video games, advertisements, and other media. CG faces vary in their degree of realism, a factor that impacts viewer reactions. Therefore, efficient control of visual realism of face images is important. ...
A gaze-based study for investigating the perception of visual realism in simulated scenes

Visual realism has been a major objective of computer graphics since the inception of the field. However, the perception of visual realism is not a well-understood process and is usually attributed to a combination of visual cues and image features that ...
An Automated Estimator of Image Visual Realism Based on Human Cognition
CVPR '14: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition

Assessing the visual realism of images is increasingly becoming an essential aspect of fields ranging from computer graphics (CG) rendering to photo manipulation. In this paper we systematically evaluate factors underlying human perception of visual ...

Comments

Information & Contributors

Information

Published In

SA '12: SIGGRAPH Asia 2012 Technical Briefs

November 2012

144 pages

ISBN:9781450319157

DOI:10.1145/2407746

Conference Chairs:
Zhengyou Zhang
Microsoft Research
,
Zhengguo Li
Institute for Infocomm Research, A*STAR

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]

In-Cooperation

SIGCHI: ACM Special Interest Group on Computer-Human Interaction

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 28 November 2012

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

SA '12

Sponsor:

SIGGRAPH

SA '12: SIGGRAPH Asia 2012

November 28 - December 1, 2012

Singapore, Singapore

Acceptance Rates

Overall Acceptance Rate 178 of 869 submissions, 20%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

13
Total Citations
View Citations
644
Total Downloads

Downloads (Last 12 months)47
Downloads (Last 6 weeks)2

Reflects downloads up to 08 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

McElvaney TOsman MMareschal I(2022)Identifying criminals: No biasing effect of criminal context on recalled threatMemory & Cognition10.3758/s13421-021-01268-w50:8(1735-1755)Online publication date: 13-Jan-2022
https://doi.org/10.3758/s13421-021-01268-w
Assaf RKunz STeixeira L(2020)The Presence of the Uncanny Valley Between Animation and CinemaMultidisciplinary Perspectives on New Media Art10.4018/978-1-7998-3669-8.ch005(97-118)Online publication date: 26-Jun-2020
https://doi.org/10.4018/978-1-7998-3669-8.ch005
Salminen JLiu YŞengün SSantos JJung SJansen BPaternò FOliver NConati CSpano LTintarev N(2020)The effect of numerical and textual information on visual engagement and perceptions of AI-driven persona interfacesProceedings of the 25th International Conference on Intelligent User Interfaces10.1145/3377325.3377492(357-368)Online publication date: 17-Mar-2020
https://dl.acm.org/doi/10.1145/3377325.3377492
Alexi JDommisse KCleary DPalermo RKloth NBell J(2019)An Assessment of Computer-Generated Stimuli for Use in Studies of Body Size Estimation and BiasFrontiers in Psychology10.3389/fpsyg.2019.0239010Online publication date: 22-Oct-2019
https://doi.org/10.3389/fpsyg.2019.02390
Farid H(2019)Image ForensicsAnnual Review of Vision Science10.1146/annurev-vision-091718-0148275:1(549-573)Online publication date: 15-Sep-2019
https://doi.org/10.1146/annurev-vision-091718-014827
Fan SNg TKoenig BHerberg JJiang MShen ZZhao Q(2018)Image Visual Realism: From Human Perception to Machine ComputationIEEE Transactions on Pattern Analysis and Machine Intelligence10.1109/TPAMI.2017.274715040:9(2180-2193)Online publication date: 1-Sep-2018
https://dl.acm.org/doi/10.1109/TPAMI.2017.2747150
Quan WWang KYan DZhang X(2018)Distinguishing Between Natural and Computer-Generated Images Using Convolutional Neural NetworksIEEE Transactions on Information Forensics and Security10.1109/TIFS.2018.283414713:11(2772-2787)Online publication date: Nov-2018
https://doi.org/10.1109/TIFS.2018.2834147
Mader BBanks MFarid H(2017)Identifying Computer-Generated Portraits: The Importance of Training and IncentivesPerception10.1177/030100661771363346:9(1062-1076)Online publication date: 22-Jun-2017
https://doi.org/10.1177/0301006617713633
Rahmouni NNozick VYamagishi JEchizen I(2017)Distinguishing computer graphics from natural images using convolution neural networks2017 IEEE Workshop on Information Forensics and Security (WIFS)10.1109/WIFS.2017.8267647(1-6)Online publication date: Dec-2017
https://doi.org/10.1109/WIFS.2017.8267647
Holmes OBanks MFarid H(2016)Assessing and Improving the Identification of Computer-Generated PortraitsACM Transactions on Applied Perception10.1145/287171413:2(1-12)Online publication date: 9-Feb-2016
https://dl.acm.org/doi/10.1145/2871714
Show More Cited By

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 Publication

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Abstract

Supplementary Material

References

Cited By

Index Terms

Recommendations

Human Perception of Visual Realism for Photo and Computer-Generated Face Images

A gaze-based study for investigating the perception of visual realism in simulated scenes

An Automated Estimator of Image Visual Realism Based on Human Cognition

Comments

Information

Published In

Sponsors

In-Cooperation

Publisher

Publication History

Permissions

Check for updates

Author Tags

Qualifiers

Conference

Acceptance Rates

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

Login options

Full Access

View options

PDF

eReader

Share

Share this Publication link

Share on social media

Affiliations