Accede a información sobre la estructura de la actividad investigadora de Geintra.
Accede a información sobre la estructura de la actividad investigadora de Geintra.
Accede a nuestra oferta actual de becas, tesis doctorales, contratos y trabajos fin de carrera.
By Adrien Bartoli, permanent CNRS research scientist at the LASMEA laboratory in Clermont-Ferrand, France, will take place on 12th and 13th of April, from 10:00 to 12:00 in the "Meeting Room 1" of the Departamento de Electrónica of Universidad de Alcalá (Edificio Politécnico).
Imagine we have a bending piece of paper or cloth being imaged by a camera. The problem we study is how to recover the 4D shape of a deformable surface from only these images. In other words, how to compute the surface's 3D shape at every image. This involves two core problems of computer vision: image registration (image matching) and 3D reconstruction (image-based scene shape recovery). In the classical setup used in stereovision, Structure-from-Motion and SLAM, the scene shape is assumed rigid and constant over time. The deformable case requires one to re-think the
constraints and tools being used. The presentation will be divided into two lectures each of two hours, where the two topics of image registration and 4D reconstruction for a deformable surface will be presented, with numerous
examples on (unordered) snapshots and videos.
Adrien Bartoli is a permanent CNRS research scientist (Chargé de Recherche) at the LASMEA laboratory in Clermont-Ferrand, France, since October 2004 and a visiting professor at DIKU in Copenhagen, Denmark for 2006-2009. Before that, he was a postdoctoral researcher at the University of Oxford, UK, in the Visual Geometry Group, under the supervision of Prof. Andrew Zisserman. He obtained his Habilitation Degree (HDR - Habilitation à Diriger des Recherches) from Université Blaise Pascal, Clermont II, in June 2008 and he did his PhD in the Perception group (ex MOVI), at INRIA Grenoble, France, under the supervision of Prof. Peter Sturm and Prof. Radu Horaud, receiving the 2004 INPG PhD thesis prize. Since September 2006, Adrien is leading the ComSee research team (with Thierry Chateau until early 2009). His main research interests are in image registration and Structure-From-Motion for rigid and non-rigid scenarios, and machine learning, within the field of Computer Vision..