Maria I. Restrepo

Learn More
—This paper presents a novel framework for surface reconstruction from multi-view aerial imagery of large scale urban scenes, which combines probabilistic volumetric modeling with smooth signed distance surface estimation, to produce very detailed and accurate surfaces. Using a continuous probabilistic volumetric model which allows for explicit(More)
must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. " [Available at IEEEXplore] Abstract—This paper(More)
✴ Characterization of the Probabilistic Volumetric Models (PVM) as a new representation for 3-d scene understanding. ✴ The first evaluation of the performance of several local shape descrip-tors extracted from the PVM in terms of accuracy for object classification. ✴ Histogram-based descriptors are of particular interest as they are the most popular and(More)
A new representation of 3-d object appearance from video sequences has been developed over the past several which combines the ideas of background modeling and volumetric multi-view reconstruction. In this representation, Gaussian mixture models for intensity or color are stored in volumetric units. This 3-d probabilistic volume model, PVM, is learned from(More)
  • 1