Similar articles

Abstract: In this paper, we propose a highly automatic approach for 3D photorealistic face reconstruction from a single frontal image. The key point of our work is the implementation of adaptive manifold learning approach. Beforehand, an active appearance model (AAM) is trained for automatic feature extraction and adaptive locally linear embedding (ALLE) algorithm is utilized to reduce the dimensionality of the 3D database. Then, given an input frontal face image, the corresponding weights between 3D samples and the image are synthesized adaptively according to the AAM selected facial features. Finally, geometry reconstruction is achieved by linear weighted combination of adaptively selected samples. Radial basis function (RBF) is adopted to map facial texture from the frontal image to the reconstructed face geometry. The texture of invisible regions between the face and the ears is interpolated by sampling from the frontal image. This approach has several advantages: (1) Only a single frontal face image is needed for highly automatic face reconstruction; (2) Compared with former works, our reconstruction approach provides higher accuracy; (3) Constraint based RBF texture mapping provides natural appearance for reconstructed face.

[1] Arad, N., Dyn, N., Reisfeld, D., Yeshurun, Y., 1994. Image warping by radial basis functions: application to facial expressions. CVGIP: Graphical Models and Image Processing, 56(2):161-172.

[2] Blanz, V., Vetter, T., 1999. A Morphable Model for the Synthesis of 3D Faces. Proc. SIGGRAPH’99. Los Angeles, p.187-194.

[3] Dimitrijevic, M., Ilic, S., Fua, P., 2004. Accurate Face Models from Uncalibrated and ILL-Lit Video Sequences. Proc. 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2:1034-1041.

[4] Hu, Y., Jiang, D., Yan, S., Zhang, L., Zhang, H., 2004. Automatic 3D Reconstruction for Face Recognition. Proc. 6th IEEE International Conference on Automatic Face and Gesture Recognition, p.843.

[5] Huang, L., Shimizu, A., Kobatake, H., 2002. Face Detection Using a Modified Radial Basis Function Neural Network. Proc. IEEE International Conference on Pattern Recognition, 2:342-345.

[6] Park, K., Zhang, H., Vezhnevets, V., Choh, H.K., 2004. Image-based Photorealistic 3D Face Modeling. Proc. 6th IEEE International Conference on Automatic Face and Gesture Recognition, p.49-54.

[7] Pighin, F., Hecker, J., Lischinski, D., Szeliski, R., Salesin, D., 1998. Synthesizing Realistic Facial Expressions from Photographs. Proc. SIGGRAPH’98. Orlando, p.75-84.

[8] Reiter, D., Donner, R., Langs, G., Bischof, H., 2006. 3D and Infrared Face Reconstruction from RGB Data Using Canonical Correlation Analysis. Proc. 18th International Conference on Pattern Recognition, p.425-428.

[9] Roweis, S., Saul, L., 2000. Nonlinear dimensionality reduction by locally linear embedding. Science, 290(5500):2323-2326.

[10] Sclaroff, S., Alon, J., 1999. Non-rigid Shape from Image Streams. Boston University, Computer Science, Technical Report, No. 99-006.

[11] Tenenbaum, J., Silva, V., Langford, J., 2000. A global geometric framework for nonlinear dimensionality reduction. Science, 290(5500):2319-2323.

[12] Tomasi, C., Kanade, T., 1992. Shape and Motion from Image Streams: A Factorization Method Full Report on the Orthographic Case. Cornell TR 92-1270 and Carnegie Mellon CMU-CS-92-104.

[13] Torresani, L., Hertzmann, A., 2003. Learning Non-rigid 3D Shape from 2D Motion. Proc. Neural Information Processing Systems. Vancouver, BC, p.1555-1562.

[14] Turk, M., Pentland, A., 1991. Eigenfaces for recognition. Journal of Cognitive Neuroscience, 3(1):71-86.

[15] Turk, G., O’Brien, J., 1999. Shape Transformation Using Variational Implicit Functions. Proc. SIGGRAPH’99, p.335-342.

[16] Wang, J., Zhang, Z., Zha, H., 2005. Adaptive Manifold Learning. Advances in Neural Information Processing Systems 17. MIT Press, Cambridge, MA, p.1473-1480.

[17] Xiao, J., Kanade, T., 2004. Non-rigid Shape and Motion Recovery: Degenerate Deformations. Proc. 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1:668-675.

[18] Yoshiki, K., Saito, H., Mochimaru, M., 2006. Reconstruction of 3D Face Model from Single Shading Image Based on Anatomical Database. Proc. 18th International Conference on Pattern Recognition, p.350-353.

[19] Zhang, R., Tsai, P., Cryer, J., Shah, M., 1999. Shape from shading: a survey. IEEE Tran. Pattern Anal. Machine Intell., 21(8):690-706.

[20] Zhang, Q., Liu, Z., Guo, B., Shum, H., 2003. Geometry-Driven Photorealistic Facial Expression Synthesis. Eurographics/SIGGRAPH Symposium on Computer Animation. San Diego, CA, p.177-186.

[21] Zhao, M., Chua, T., Sim, T., 2006. Morphable Face Reconstruction with Multiple Images. Proc. 7th International Conference on Automatic Face and Gesture Recognition, p.597-602.