We propose a hybrid body representation that represents each typical pose by both template-like view information and part-based structural information. Specifically, each body par...
This paper presents a novel human-computer interface for projector/camera-based applications that uses a deformable interaction surface. We discuss its design and implementation w...
In this paper, we consider the problem of compositing a scene from multiple images. Multiple images, for example, can be obtained by varying the exposure of the camera, by changin...
Many computer vision algorithms limit their performance by ignoring the underlying 3D geometric structure in the image. We show that we can estimate the coarse geometric propertie...
The robust regression techniques in the RANSAC family are popular today in computer vision, but their performance depends on a user supplied threshold. We eliminate this drawback ...