Using optical triangulation methods to measure the shape of translucent objects is difficult because subsurface scattering contaminates measurements of the “direct” reflecti...
Traditional computer vision and machine learning algorithms have been largely studied in a centralized setting, where all the processing is performed at a single central location....
We introduce a nonparametric representation for graphical model on trees which expresses marginals as Hilbert space embeddings and conditionals as embedding operators. This formul...
The scene flow in binocular stereo setup is estimated using a seed growing algorithm. A pair of calibrated and synchronized cameras observe a scene and output a sequence of image...
Single sensor digital cameras capture one color value for every pixel location. The remaining two color channel values need to be estimated to obtain a complete color image. This ...