Object class models trained on hundreds or thousands of
images have shown to enable robust detection. Transferring
knowledge from such models to new object classes trained
from ...
The human vision system can interpret a single 2D line drawing as a 3D object without much difficulty even if the hidden lines of the object are invisible. Several reconstruction ...
Most dense stereo correspondence algorithms start by establishing discrete pixel matches and later refine these matches to sub-pixel precision. Traditional sub-pixel refinement me...
We present a framework for calculating low-dimensional bases to represent image irradiance from surfaces with isotropic reflectance under arbitrary illumination. By representing t...
This paper addresses the problem of calibrating a pinhole camera from images of an isoceles trapezoid. Assuming a unit aspect ratio and zero skew, we introduce a novel and simple ...