We present an algorithm for color classification with explicit illuminant estimation and compensation. A Gaussian classifier is trained with color samples from just one training im...
Estimating photo-consistency is one of the most important ingredients for any 3D stereo reconstruction technique that is based on a volumetric scene representation. This paper pres...
This paper presents a geometric approach to recognizing smooth objects from their outlines. We define a signature function that associates feature vectors with objects and baseline...
Svetlana Lazebnik, Amit Sethi, Cordelia Schmid, Da...
Abstract. Regularization o ers a powerful framework for signal reconstruction by enforcing weak constraints through the use of stabilizers. Stabilizers are functionals measuring th...
This paper presents a computational model that segments images based on the textural properties of object surfaces. The proposed Coupled-Membrane model applies the weak membrane ap...