Keynote Speakers

Jean-Philippe Pons, Acute3D

Title: 3D urban and architectural reconstruction: computational geometry can help
Abstract: In the first part of this talk, I will present our work on high resolution 3D reconstruction from photographs and its applications to 3D architectural and urban modeling from ground or aerial imagery. Our method leverages computational geometry, combinatorial optimization and GPU computing to handle large-scale scenes, without human intervention, in a few minutes/hours of computation time. The accuracy and completeness of the obtained 3D models make our method an excellent alternative to laser scanning in the architectural modeling pipeline. I will describe how this technology has evolved in the recent years from a research prototype to a robust solution offered to public and professional end-users by a leading CAD software company. In the second part of this talk, I will describe our more recent work on directly and automatically producing a concise and idealized 3D representation from unstructured point data of complex cluttered real-world scenes, with a high level of noise and a significant proportion of outliers. A major contribution of our work is an adaptive decomposition of 3D space induced by planar primitives, namely a polyhedral cell complex.

Katsushi Ikeuchi, The University of Tokyo

Title: Cloud museum and e-Heritage
Abstract: will be given soon.

Radu Rusu, Michael Dixon, Suat Gedikli and Patrick Mihelich, Willow Garage

Title: Advanced 3D Image Processing with Point Cloud Library
Abstract: will be given soon.