Large scale reconstruction has been an active research area for almost three decades. Conventional approaches are based on the multi-view principle where scenes are viewed from different viewpoints which ones being put in correspondence allow through geometric principles the recovery of scene geometry. In this lecture we will present a novel, approach for large scale scene modeling through grammars. The central idea will be to represent man-made buildings as a derivation sequence of a shape grammar allowing scalable, modular and 2.5D reconstruction from 2D images. To this end, we develop novel learning methods allowing the extraction of typology specific procedural generative processes from training examples using generic shape grammars as well as novel inference methods towards parsing images through these grammars either in 2D or 3D. Promising results demonstrate the extreme potentials of our method.
Nikos Paragios (42) is professor of Applied Mathematics and Computer Science, director of the Center for Visual Computing of Ecole Centrale de Paris, and scientific leader of GALEN group of Ecole Centrale de Paris/Inria at the Saclay, Ile-de-France Unit. Prior to that he was professor (2004-2005, 2011-2013) at the Ecole Nationale de Ponts et Chaussees, affiliated with Siemens Corporate Research (Princeton, NJ, 1999-2004) as a project manager, senior research scientist and research scientist (1999-2004). N. Paragios was an adjunct professor at Rutgers (2002) and at New York University (2004) and a visiting professor at Yale ( 2007) and at University of Houston (2009). Professor Paragios is a fellow of IEEE and senior fellow of the Institut Universitaire de France (2014-2019), has co-edited four books, published more than two hundred papers in the most prestigious journals and conferences of medical imaging and computer vision (DBLP server), and holds twenty three US patents. His work has approx 13,500 citations according to Google Scholar and his H-number (01/2015) is 55. Professor Paragios is the Editor in Chief of the Computer Vision and Image Understanding Journal (CVIU) and serves as a member of the editorial board for the Medical Image Analysis Journal (MedIA) and the SIAM Journal in Imaging Sciences (SIIMS). He has served as an associate/area editor/member of the editorial board for the IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), the Computer Vision and Image Understanding Journal (CVIU), the International Journal of Computer Vision (IJCV) and the Journal of Mathematical Imaging and Vision (JMIV) while he was one of the program chairs of the 11th European Conference in Computer Vision (ECCV'10, Heraklion, Crete) and serves regularly at the conference boards of the most prestigious events of his fields (ICCV, CVPR, ECCV, MICCAI). Professor Paragios is member of the scientific council of SAFRAN conglomerate.
