ABSTRACT
Our goal is to generate novel realistic images of faces using a model trained from real examples. This model consists of two components: First we consider face images as samples from a texture with spatially varying statistics and describe this texture with a local non-parametric model. Second, we learn a parametric global model of all of the pixel values. To generate realistic faces, we combine the strengths of both approaches and condition the local non-parametric model on the global parametric model. We demonstrate that with appropriate choice of local and global models it is possible to reliably generate new realistic face images that do not correspond to any individual in the training data. We extend the model to cope with considerable intra-class variation (pose and illumination). Finally, we apply our model to editing real facial images: we demonstrate image in-painting, interactive techniques for improving synthesized images and modifying facial expressions.
Supplemental Material
Available for Download
Supplementary video for the paper "Visio-lization: Generating Novel Facial Images".
- Agarwala, A., Dontcheva, M., Agrawala, M., Drucker, S., Colburn, A., Curless, B., Salesin, D., and Cohen, M. 2004. Interactive digital photomontage. ACM Transactions on Graphics (Proc. SIGGRAPH) 23, 3, 294--302. Google ScholarDigital Library
- Ashikhmin, M. 2001. Synthesizing natural textures. In Proc. ACM Symposium on Interactive 3D Graphics, 217--226. Google ScholarDigital Library
- Bishop, C. 2006. Pattern Recognition and Machine Learning. Springer. Google ScholarDigital Library
- Bitouk, D., Kumar, N., Dhillon, S., Belhumeur, P., and Nayar, S. K. 2008. Face swapping: automatically replacing faces in photographs. ACM Trans. Graph. 27, 3, 1--8. Google ScholarDigital Library
- Blanz, V., and Vetter, T. 1999. A morphable model for the synthesis of 3d faces. In Proceedings of ACM SIGGRAPH 99, 187--194. Google ScholarDigital Library
- Blanz, V., Albrecht, I., Haber, J., and Seidel, H.-P. 2006. Creating face models from vague mental images. Computer Graphics Forum 25, 3, 645--654.Google ScholarCross Ref
- Brand, M., and Pletscher, P. 2008. A conditional random field for photo editing. In Proceedings of CVPR, 187--194.Google Scholar
- Bregler, C., Covell, M., and Slaney, M. 1997. Video rewrite: Driving visual speech with audio. In Proceedings of ACM SIGGRAPH 97, 353--360. Google ScholarDigital Library
- Dedeoglu, G., Kanade, T., and August, J. 2004. Highzoom video hallucination by exploiting spatio-temporal regularities. In Proceedings of CVPR, 151--158. Google ScholarDigital Library
- Dempster, A. P., Laird, N. M., and Rubin, D. B. 1977. Maximum likelihood for incomplete data via the EM algorithm. Journal of the Royal Statistical Society 39 (B), 1, 1--38.Google Scholar
- Diakopoulos, N., Essa, I., and Jain, R. 2004. Content based image synthesis. In CIVR 04, 299--307.Google Scholar
- Efros, A. A., and Freeman, W. T. 2001. Image quilting for texture synthesis and transfer. In Proceedings of ACM SIGGRAPH, 341--346. Google ScholarDigital Library
- Efros, A. A., and Leung, T. K. 1999. Texture synthesis by non-parametric sampling. In Proceedings of ICCV, vol. 2, 1033--1038. Google ScholarDigital Library
- Ezzat, T., Geiger, G., and Poggio, T. 2002. Trainable videorealistic speech animation. In Proceedings of ACM SIGGRAPH 2002, 388--398. Google ScholarDigital Library
- Ghahramani, Z., and Hinton, G. E. 1997. The EM algorithm for mixtures of factor analyzers. Technical Report CRG-TR-96-1, Dept. of Computer Science, University of Toronto, Canada.Google Scholar
- Hays, J., and Efros, A. A. 2007. Scene completion using millions of photographs. ACM Transactions on Graphics (Proc. SIGGRAPH) 26, 3, 4:1--4:7. Google ScholarDigital Library
- Kwatra, V., Schödl, A., Essa, I., Turk, G., and Bobick, A. 2003. Graphcut textures: Image and video synthesis using graph cuts. ACM Transactions on Graphics 22, 3, 277--286. Google ScholarDigital Library
- Lalonde, J., Hoiem, D., Efros, A. A., Rother, C., Winn, J., and Criminisi, A. 2007. Photo clip art. ACM Transactions on Graphics (Proc. SIGGRAPH) 26, 3, 3:1--3:10. Google ScholarDigital Library
- Liu, W., Lin, D., and Tang, X. 2005. Hallucinating faces: Tensorpatch super-resolution and coupled residue compensation. In Proceedings of CVPR, 478--484. Google ScholarDigital Library
- Liu, C., Shum, H., and Freeman, W. 2007. Face hallucination: theory and practice. International Journal of Computer Vision 75, 1, 115--134. Google ScholarDigital Library
- Messer, K., Matas, J., Kittler, J., Luettin, J., and Maitre, G. 1999. XM2VTSbd: The extended MTVTS database. In Proceedings 2nd Conference on Audio and Videobase Biometric Personal Verification (AVBPA99), 72--77.Google Scholar
- Nguyen, M., Lalonde, J., Efros, A., and La Torre, F. D. 2008. Image-based shaving. Computer Graphics Forum (Eurographics) 27, 2, 627--635.Google ScholarCross Ref
- Perez, P., Gangnet, M., and Blake, A. 2003. Poisson image editing. ACM Transactions on Graphics (Proc. SIGGRAPH) 22, 3, 313--318. Google ScholarDigital Library
- Prince, S., Elder, J., Warrell, J., and Felisberti, F. 2008. Tied factor analysis for face recognition across large pose differences. IEEE Pattern Recognition and Machine Intelligence 30, 6, 970--984. Google ScholarDigital Library
- Tenenbaum, J., and Freeman, W. 2000. Separating style and content with bilinear models. Neural Computation 12, 6, 1247--1283. Google ScholarDigital Library
- Turk, M. A., and Pentland, A. P. 1991. Face recognition using eigenfaces. In Proceedings of CVPR, 586--591.Google Scholar
- Vlasic, D., Brand, M., Pfister, H., and Popovic, J. 2005. Face transfer with multiliner models. ACM Transactions on Graphics (Proc. SIGGRAPH) 24, 3, 426--433. Google ScholarDigital Library
- Wei, L., and Levoy, M. 2000. Fast texture synthesis using tree-structured vector quantization. In Proceedings of ACM SIGGRAPH 2000, 479--488. Google ScholarDigital Library
- Weyrich, T., Matusik, W., Pfister, H., Bickel, B., Donner, C., Tu, C., McAndless, J., Lee, J., Ngan, A., Jensen, H., and Gross, M. 2006. Analysis of human faces using a measurement-based skin reflectance model. ACM Transactions on Graphics (Proc. SIGGRAPH) 25, 3, 1013--1024. Google ScholarDigital Library
Index Terms
- Visio-lization: generating novel facial images
Recommendations
Visio-lization: generating novel facial images
Our goal is to generate novel realistic images of faces using a model trained from real examples. This model consists of two components: First we consider face images as samples from a texture with spatially varying statistics and describe this texture ...
Frontal face synthesis based on multiple pose-variant images for face recognition
ICB'07: Proceedings of the 2007 international conference on Advances in BiometricsPose variance remains a challenging problem for face recognition. In this paper, a stereoscopic synthesis method for generating a frontal face image is proposed to improve the performance of automatic face recognition system. Through this method, a ...
Extended SRC: Undersampled Face Recognition via Intraclass Variant Dictionary
Sparse Representation-Based Classification (SRC) is a face recognition breakthrough in recent years which has successfully addressed the recognition problem with sufficient training images of each gallery subject. In this paper, we extend SRC to ...
Comments