Coupled Statistical Face Reconstruction
We present a coupled statistical model that can be used to accurately recover facial surfaces from single images by jointly capturing variations in surface normal direction and surface height. The model is trained on range data. By fitting the model to surface normal data, the surface height function is implicitly recovered without having to integrate the recovered field of surface normals. We show how the coupled model can be fitted to image brightness data using geometric constraints on surface normal direction furnished by Lambert’s law.
Unable to display preview. Download preview PDF.
- 2.Zhao, W.Y., Chellappa, R.: Illumination-insensitive face recognition using symmetric SFS. In: Proc. CVPR, pp. 286–293 (2000)Google Scholar
- 4.Dovgard, R., Basri, R.: Statistical symmetric shape from shading for 3D structure recovery of faces. In: Proc. 8th European Conference on Computer Vision, vol. 2nd, pp. 99–113 (2004)Google Scholar
- 7.Sirovich, L.: Turbulence and the dynamics of coherent structures. Quart. Applied Mathematics XLV, 561–590 (1987)Google Scholar
- 9.Georghiades, A., Belhumeur, P., Kriegman, D.: From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE Trans. PAMI 23, 643–660 (2001)Google Scholar
- 10.Smith, W., Robles-Kelly, A., Hancock, E.R.: Reflectance correction for perspiring faces. In: Proc. ICIP, pp. 1389–1392 (2004)Google Scholar