Shape and reflectance from natural illumination
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Color constancy, intrinsic images, and shape estimation
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
| Hi-index | 0.00 |
The traditional shape-from-shading problem, with a single light source and Lambertian reflectance, is challenging since the constraints implied by the illumination are not sufficient to specify local orientation. Photometric stereo algorithms, a variant of shape-from-shading, simplify the problem by controlling the illumination to obtain additional constraints. In this paper, we demonstrate that many natural lighting environments already have sufficient variability to constrain local shape. We describe a novel optimization scheme that exploits this variability to estimate surface normals from a single image of a diffuse object in natural illumination. We demonstrate the effectiveness of our method on both simulated and real images.