We develop a local image-correspondence algorithm which performs well near occluding boundaries. Unlike traditional robust methods, our method can find correspondences when the on...
Image fusion is the process of extracting meaningful visual information from two or more images and combinining them to form one fused image. Image fusion is important within many...
Paul R. Hill, David R. Bull, Cedric Nishan Canagar...
We view the task of change detection as a problem of object recognition from learning. The object is defined in a 3D space where the time is the 3rd dimension. We propose two com...
Directional information is an important component of both natural and synthetic images, and it is exploited in many image processing applications. Directional basis analysis is us...
It’s common experience for human vision to perceive full 3D shape and scene from a single 2D image with the occluded parts “filled-in” by prior visual knowledge. In this pa...