We propose an unconventional but highly effective approach
to robust fitting of multiple structures by using statistical
learning concepts. We design a novel Mercer kernel
for t...
A method is presented to recover 3D scene structure and camera motion from multiple images without the need for correspondence information. The problem is framed as finding the ma...
Frank Dellaert, Steven M. Seitz, Charles E. Thorpe...
We introduce a theoretical framework and practical algorithms for replacing time-coded structured light patterns with viewpoint codes, in the form of additional camera locations. ...
Mark Young, Erik Beeson, James Davis, Szymon Rusin...
Abstract. This paper extends the recovery of structure and motion to image sequences with several independently moving objects. The motion, structure, and camera calibration are al...
In this paper we describe work on the automatic recognition of island structures. In an initial phase several test persons were asked to mark groups of islands that they perceived...