We propose a variational multigrid method for fast 3D interpretation of image sequences, in which a dense depth map and 3D motion are directly recovered from spatiotemporal change...
This paper describes an efficient vision-based global topological localization approach that uses a coarse-tofine strategy. Orientation Adjacency Coherence Histogram (OACH), a nov...
Most illuminant estimation algorithms worked on point light sources or directional light sources. Little attempt has been made, however, to estimate area light sources. In this pa...
We present a document-specific OCR system and apply it to a corpus of faxed business letters. Unsupervised classification of the segmented character bitmaps on each page, using a ...
We present an algorithm able to register a known 3D deformable model to a set of 2D matched points extracted from a single image. Unlike previous approaches, the problem is solved...