Approximating 3D Facial Shape from Photographs Using Coupled Statistical Models
In this paper we focus on the problem of developing a coupled statistical model that can be used to recover surface height from frontal photographs of faces. The idea is to couple intensity and height by jointly modeling their combined variations. We perform Principal Component Analysis (PCA) on the shape coefficients for both intensity and height training data in order to construct the coupled statistical model. Using the best-fit coefficients of an intensity image, height information can be implicitly recovered through the coupled statistical model. Experiments show that the method can generate good approximations of the facial surface shape from out-of-training photographs of faces.
Unable to display preview. Download preview PDF.
- 1.Bors, A.G., Hancock, E.R., Wilson, R.C.: Terrain analysis using radar shape-from-shading. IEEE Trans. on Pattern Analysis and Machine Intelligence 25(5) (2003)Google Scholar
- 3.Wu, Z., Li, L.: A line integration based method for depth recovery from surface normals. CVGIP 43(1), 53–66 (1988)Google Scholar
- 4.Zhao, W., Chellapa, R.: Illumination-insensitive face recognition using symmetric shape-from-shading. In: Proc. Conference on Computer Vision and Pattern Recognition, pp. 286–293 (2000)Google Scholar
- 5.Samaras, D., Metaxas, D.: Incorporating illumination constraints in deformable models for shape and light direction estimation. IEEE Trans. PAMI 25(2), 247–264 (2003)Google Scholar
- 6.Castelán, M., Hancock, E.: Acquiring height maps of faces from a single image. In: Proc. IEEE 3DPVT, pp. 183–190 (2004)Google Scholar
- 7.Prados, E., Camilli, F., Faugeras, O.: A unifying and rigorous shape from shading method adapted to realistic data and applications. Journal of Mathematical Imaging and Vision (2006)Google Scholar
- 9.Dovgard, R., Basri, R.: Statistical symmetric shape from shading for 3d structure recovery of faces. In: Proc. European Conference on Computer Vision, May 2004, pp. 99–113 (2004)Google Scholar
- 11.Cootes, T.F., Edwards, G.C., Taylor, C.J.: Active appearance models. In: Proc. European Conference in Computer Vision, pp. 484–498 (1998)Google Scholar
- 12.Turk, M., Pentland, A.: Face recognition using eigenfaces. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 586–591 (1991)Google Scholar
- 13.Sirovich, L., Everson, R.: Management and analysis of large scientific datasets. The International Journal of Supercomputer Applications 6(1), 50–68 (1992)Google Scholar
- 15.Georghiades, A., Belhumeur, D., Kriegman, D.: From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE Transactions on Pattern Analysis and Machine Intelligence, 634–660 (2001)Google Scholar