Reflectance and Natural Illumination from a Single Image
Estimating reflectance and natural illumination from a single image of an object of known shape is a challenging task due to the ambiguities between reflectance and illumination. Although there is an inherent limitation in what can be recovered as the reflectance band-limits the illumination, explicitly estimating both is desirable for many computer vision applications. Achieving this estimation requires that we derive and impose strong constraints on both variables. We introduce a probabilistic formulation that seamlessly incorporates such constraints as priors to arrive at the maximum a posteriori estimates of reflectance and natural illumination. We begin by showing that reflectance modulates the natural illumination in a way that increases its entropy. Based on this observation, we impose a prior on the illumination that favors lower entropy while conforming to natural image statistics. We also impose a prior on the reflectance based on the directional statistics BRDF model that constrains the estimate to lie within the bounds and variability of real-world materials. Experimental results on a number of synthetic and real images show that the method is able to achieve accurate joint estimation for different combinations of materials and lighting.
KeywordsGround Truth Single Image Lighting Environment Photometric Stereo Functional Principal Component Analysis
Unable to display preview. Download preview PDF.
- 1.Ramamoorthi, R., Hanrahan, P.: A signal-processing framework for inverse rendering. In: Proc. of ACM SIGGRAPH, pp. 117–128 (2001)Google Scholar
- 2.Chandraker, M., Ramamoorthi, R.: What an image reveals about material reflectance. In: ICCV, pp. 1–8 (2011)Google Scholar
- 8.Marschner, S., Greenberg, D.: Inverse lighting for photography. In: IS&T/SID Fifth Color Imaging Conference, pp. 262–265. The Society for Imaging Science and Technology (1997)Google Scholar
- 9.Nishino, K., Ikeuchi, K., Zhang, Z.: Re-rendering from a sparse set of images. Technical Report DU-CS-05-12, Dept. of Computer Science, Drexel University (2005)Google Scholar
- 11.Nishino, K.: Directional Statistics BRDF Model. In: ICCV, pp. 476–483 (2009)Google Scholar
- 13.Huang, J., Mumford, D.: Statistics of natural images and models. In: CVPR, pp. 541–547 (1999)Google Scholar
- 14.Alldrin, N.G., Mallick, S.P., Kriegman, D.J.: Resolving the generalized bas-relief ambiguity by entropy minimization. In: CVPR, pp. 1–7 (June 2007)Google Scholar
- 16.Rusinkiewicz, S.: A New Change of Variables for Efficient BRDF Representation. In: Eurographics Workshop on Rendering, pp. 11–22 (1998)Google Scholar
- 17.Lombardi, S., Nishino, K.: Single image multimaterial estimation. In: CVPR, pp. 238–245 (2012)Google Scholar
- 22.Debevec, P.: Rendering synthetic objects into real scenes: bridging traditional and image-based graphics with global illumination and high dynamic range photography. In: Proc. of ACM SIGGRAPH, pp. 189–198 (1998)Google Scholar