ACM Home Page
Please provide us with feedback. Feedback
Face swapping: automatically replacing faces in photographs
Full text PdfPdf (16.79 MB)
Source
ACM Transactions on Graphics (TOG) archive
Volume 27 ,  Issue 3  (August 2008) table of contents
Proceedings of ACM SIGGRAPH 2008
SESSION: Faces & reflectance table of contents
Article No. 39  
Year of Publication: 2008
ISSN:0730-0301
Also published in ...
Authors
Dmitri Bitouk  Columbia University
Neeraj Kumar  Columbia University
Samreen Dhillon  Columbia University
Peter Belhumeur  Columbia University
Shree K. Nayar  Columbia University
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 44,   Downloads (12 Months): 338,   Citation Count: 2
Additional Information:

abstract   references   cited by   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/1360612.1360638
What is a DOI?

ABSTRACT

In this paper, we present a complete system for automatic face replacement in images. Our system uses a large library of face images created automatically by downloading images from the internet, extracting faces using face detection software, and aligning each extracted face to a common coordinate system. This library is constructed off-line, once, and can be efficiently accessed during face replacement. Our replacement algorithm has three main stages. First, given an input image, we detect all faces that are present, align them to the coordinate system used by our face library, and select candidate face images from our face library that are similar to the input face in appearance and pose. Second, we adjust the pose, lighting, and color of the candidate face images to match the appearance of those in the input image, and seamlessly blend in the results. Third, we rank the blended candidate replacements by computing a match distance over the overlap region. Our approach requires no 3D model, is fully automatic, and generates highly plausible results across a wide range of skin tones, lighting conditions, and viewpoints. We show how our approach can be used for a variety of applications including face de-identification and the creation of appealing group photographs from a set of images. We conclude with a user study that validates the high quality of our replacement results, and a discussion on the current limitations of our system.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

1
2
 
3
 
4
Blanz, V., Scherbaum, K., Vetter, T., and Seidel, H.-P. 2004. Exchanging Faces in Images. Computer Graphics Forum 23, 669--676.
5
 
6
 
7
8
9
10
 
11
Gross, R., Sweeney, L., de la Torre, F., and Baker, S. 2006. Model-Based Face De-Identification. 161--168.
12
 
13
Kundur, D., and Hatzinakos, D. 1996. Blind image deconvolution. IEEE Signal Processing Magazine, 3, 43--64.
 
14
Lanitis, I., Draganova, C., and Christodoulou, C. 2004. Comparing different classifiers for automatic age estimation. IEEE Trans. on Systems, Man, and Cybernetics, B 34, 621--628.
15
 
16
Malik, S., 2003. Digital face replacement in photographs. http://www.cs.toronto.edu/~smalik/2530/project/results.html.
 
17
 
18
 
19
Omron, 2007. OKAO vision. http://omron.com/rd/vision/01.html.
20
 
21
 
22
 
23
Wang, Y., Liu, Z., Hua, G., Wen, Z., Zhang, Z., and Samaras, D. 2007. Face re-lighting from a single image under harsh lighting conditions. CVPR '07.
 
24
Wen, Z., Liu, Z., and Huang., T. S. 2003. Face Relighting with Radiance Environment Maps. In CVPR '03, 158--165.


Collaborative Colleagues:
Dmitri Bitouk: colleagues
Neeraj Kumar: colleagues
Samreen Dhillon: colleagues
Peter Belhumeur: colleagues
Shree K. Nayar: colleagues