We analyze the least?squares error for structure from motion with a single infinitesimal motion ("structure from optical flow"). We present asymptotic approximations to ...
An important theoretical tool in machine learning is the bias/variance decomposition of the generalization error. It was introduced for the mean square error in [3]. The bias/vari...
We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...
The problem of finding clusters in data is challenging when clusters are of widely differing sizes, densities and shapes, and when the data contains large amounts of noise and out...
Digital photography has the potential to supersede conventional film photography. In order to realize this potential, digital photography needs to provide the best image quality a...