We show that the set of all ow- elds in a sequence of frames imaging a rigid scene resides in a lowdimensional linear subspace. Based on this observation, we develop a method for ...
We introduce a novel energy minimization method to decompose a video into a set of super-resolved moving layers. The proposed energy corresponds to the cost of coding the sequence...
We present a fast line segment tracker which does not require any knowledge about the motion of the camera nor the structure of the observed scene. It runs on 320 x 240 pixel imag...
Peer Neubert, Peter Protzel, Teresa Vidal-Calleja,...
Recent research in image sensors has produced cameras with very large fields of view. A n area of computer vision research which will benefit from this technology is the computati...
Abstract. This paper addresses the problem of motion estimation and reconstruction of 3D models from profiles of an object rotating on a turntable, obtained from a single camera. I...