In the standard scale space approach one obtains a scale space representation u : Rd R+ → R of an image f ∈ L2(Rd ) by means of an evolution equation on the additive group (Rd ...
High dimensional data that lies on or near a low dimensional manifold can be described by a collection of local linear models. Such a description, however, does not provide a glob...
Sam T. Roweis, Lawrence K. Saul, Geoffrey E. Hinto...
Recent research on point-based surface representations suggests that point sets may be a viable alternative to parametric surface representations in applications where the topolog...
We describe a novel and robust feature descriptor called ordinal spatial intensity distribution (OSID) which is invariant to any monotonically increasing brightness changes. Many t...
Determining the correspondence of image patches is one of the most important problems in Computer Vision. When the intensity space is variant due to several factors such as the ca...