Feature space analysis is the main module in many computer vision tasks. The most popular technique, k-means clustering, however, has two inherent limitations: the clusters are co...
We present a new Gaussian Process inference algorithm, called Online Sparse Matrix Gaussian Processes (OSMGP), and demonstrate its merits with a few vision applications. The OSMGP ...
This paper considers a fundamental problem in visual motion perception, namely the problem of egomotion estimation based on visual input. Many of the existing techniques for solvin...
A richer set of land-cover classes are observable in satellite imagery than ever before due to the increased sub-meter resolution. Individual objects, such as cars and houses, are...
Piecewise constant and piecewise smooth Mumford-Shah (MS) models have been widely studied and used for image segmentation. More complicated than piecewise constant MS, global Gaus...