Self-calibration is one of the most active issues concerning vision-based 3D measurements. However, in the case of the light sectioning method, there has been little research cond...
A novel approach to scene categorization is proposed. Similar to previous works of [11, 15, 3, 12], we introduce an intermediate space, based on a low dimensional semantic "t...
In this paper we propose a novel Conditional Random Field (CRF) formulation for the semantic scene labeling problem which is able to enforce temporal consistency between consecuti...
Light power is a ected when it crosses the atmosphere; there is a simple, albeit non-linear, relationship between the radiance of an image at any given wavelength and the distance...
Image mosaics are useful for a variety of tasks in vision and computer graphics. A particularly convenient way to generate mosaics is by `stitching' together many ordinary ph...