Model-Based Ambient Occlusion for Inverse Rendering
Conference paper
Abstract
We present a novel framework to inverse render faces in arbitrary complex illumination with a 3D morphable model. Compared to previously introduced methods, we specifically take self-occlusion into account and demonstrate that this improves the fitting accuracy by about 10%. Motivated by this observation, we design a generative statistical model of ambient occlusion. We examine generalisation error of the model and propose two ways how ambient occlusion can be inferred from shape. The proposed methods are incorporated into an existing framework to inverse render faces. We show qualitative and quantitative results for the proposed extensions and compare it with a reference method.
Keywords
Joint Model Ground Truth Data Morphable Model Ambient Occlusion Generative Statistical Model
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Preview
Unable to display preview. Download preview PDF.
References
- 1.Zhang, L., Samaras, D.: Face recognition from a single training image under arbitrary unknown lighting using spherical harmonics. IEEE Trans. Pattern Anal. Mach. Intell. 28, 351–363 (2006)CrossRefGoogle Scholar
- 2.Romdhani, S., Vetter, T.: Estimating 3D shape and texture using pixel intensity, edges, specular highlights, texture constraints and a prior. In: Proc. CVPR, vol. 2, pp. 986–993 (2005)Google Scholar
- 3.Aldrian, O., Smith, W.A.P.: Inverse rendering in suv space with a linear texture model. In: ICCV Workshop, Color and Photometry in Computer Vision (2011)Google Scholar
- 4.Aldrian, O., Smith, W.A.P.: Inverse rendering with a morphable model: A multilinear approach. In: Proceedings of the British Machine Vision Conference, pp. 88.1–88.10. BMVA Press (2011)Google Scholar
- 5.Ramamoorthi, R., Hanrahan, P.: A signal-processing framework for inverse rendering. In: SIGGRAPH 2001: Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques, pp. 117–128. ACM, New York (2001)CrossRefGoogle Scholar
- 6.Ramamoorthi, R.: Modeling illumination variation with spherical harmonics. In: Face Processing: Advanced Modeling and Methods. Academic Press (2005)Google Scholar
- 7.Visual Computing Laboratory, Institute of the National Research Council of Italy: Meshlab (2011), http://meshlab.sourceforge.net/
- 8.University of Southern California: High-resolution light probe image gallery (2011), http://gl.ict.usc.edu/Data/HighResProbes
- 9.Pharr, M., Humphreys, G.: Physically Based Rendering: From Theory to Implementation. Morgan Kaufmann, Elsevier Science (2010)Google Scholar
- 10.Fletcher, P.T., Joshi, S., Lu, C., Pizer, S.M.: Principal geodesic analysis for the study of nonlinear statistics of shape. IEEE Trans. Med. Imaging 23, 995–1005 (2004)CrossRefGoogle Scholar
- 11.Tipping, M.E., Bishop, C.M.: Probabilistic principal component analysis. Journal of the Royal Statistical Society, Series B 61, 611–622 (1999)MathSciNetzbMATHCrossRefGoogle Scholar
- 12.Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: Proc. SIGGRAPH, pp. 187–194 (1999)Google Scholar
- 13.Smith, W.A.P., Hancock, E.R.: Recovering facial shape using a statistical model of surface normal direction. IEEE Trans. Pattern Anal. Mach. Intell. 28, 1914–1930 (2006)CrossRefGoogle Scholar
- 14.Rasmussen, C.E., Williams, C.K.I.: Gaussian processes for machine learning. Adaptive computation and machine learning. MIT Press (2006)Google Scholar
- 15.Paysan, P., Knothe, R., Amberg, B., Romdhani, S., Vetter, T.: A 3D face model for pose and illumination invariant face recognition. In: Proc. IEEE Intl. Conf. on Advanced Video and Signal based Surveillance (2009)Google Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 2012