Tracking objects using the mean shift method is performed by iteratively translating a kernel in the image space such that the past and current object observations are similar. Tr...
In this paper we introduce two new methods for solving binary quadratic problems. While spectral relaxation methods have been the workhorse subroutine for a wide variety of comput...
Large-scale 3D reconstruction has recently received much attention from the computer vision community. Bundle adjustment is a key component of 3D reconstruction problems. However,...
We present variable-aperture photography, a new method for analyzing sets of images captured with different aperture settings, with all other camera parameters fixed. We show that...
A general methodology for noise reduction and contrast enhancement in very noisy image data with low dynamic range is presented. Video footage recorded in very dim light is especi...
Henrik Malm, Magnus Oskarsson, Eric Warrant, Petri...