Computational vision algorithms are often developed in a Bayesian framework. Two estimators are commonly used: maximum a posteriori (MAP), and minimum mean squared error (MMSE). W...
We present an approach for recovering the reflectance
of a static scene with known geometry from a collection of
images taken under distant, unknown illumination. In con-
trast ...
Christian Fuchs, Hans-Peter Seidel, Hendrik P. A. ...
This paper describes a new approach to neural network implementation of photometric stereo for a rotational object with non-uniform reflectance factor. Three input images are acqu...
Yuji Iwahori, Yumi Watanabe, Robert J. Woodham, Ak...
The retinex algorithm for lightness and color constancy is extended to include 3-dimensional spatial information reconstructed from a stereo image. A key aspect of traditional ret...
A 3D super-resolution algorithm is proposed below, based on a probabilistic interpretation of the ndimensional version of Papoulis' generalized sampling theorem. The algorith...
Hassan Shekarforoush, Marc Berthod, Josiane Zerubi...