High-level generative models provide elegant descriptions of videos and are commonly used as the inference framework in many unsupervised motion segmentation schemes. However, app...
Segmentation of motion in an image sequence is one of the most challenging problems in image processing, while at the same time one that finds numerous applications. To date, a wea...
A nice presentation by Daniel Cremers at the European Conference on Computer Vision (ECCV) 2006, covering a wide range of computer vision applications that the level set methods ca...
In this paper, temporal segmentation of 3D video based on motion analysis is presented. 3D video is a sequence of 3D models made for a real-world dynamic object. A modified shape ...
Abstract. We propose to tackle the optical flow problem by a combination of two recent advances in the computation of dense correspondences, namely the incorporation of image segme...
Michael Bleyer, Christoph Rhemann, Margrit Gelautz