Home

Research

Teaching

Publications

Codes

Links


Florent Lafarge

 Geometrica research group, INRIA
2004 routes des Lucioles
06902 Sophia Antipolis, France

email: florent(dot)lafarge(at)inria(dot)fr
ph:  +33 (0)4 92 38 77 31
fax: +33 (0)4 97 15 53 95

 

 

 

 

 

 


Research interest
 The first part of my research is devoted to stochastic approaches based on Markov Random Field modeling, Monte Carlo sampling and statistical learning. The second part concerns the analysis of urban scenes which includes classification, 3D-reconstruction and synthesis of objects as buildings or vegetation.



Bio

2004-2007 PhD in applied mathematics at the Matis laboratory, IGN, Paris, France
2007-2008 PostDoc at the Department of Computer Science, University of Auckland, New Zealand
2008-2009 PostDoc at the Imagine lab, ENPC, Paris, France
Since 2009 Permanent researcher at INRIA Sophia Antipolis Mediterranee, France



Students

Yannick Verdie PhD candidate, 2010-2013



Recent publications
 

Creating large-scale city models from 3D-point clouds: a robust approach with hybrid representation
 Lafarge F. and Mallet C.
International Journal of Computer Vision, to appear, 2012

 

Building large urban environments from unstructured point data (paper, poster)
 Lafarge F. and Mallet C.
Proceedings of the IEEE International Conference on Computer Vision, Barcelona, Spain, 2011

 

Geometric Feature Extraction by a Multi-Marked Point Process (paper)
Lafarge F., Gimel'farb G. and Descombes X.
IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 32(9): pages 1597-1609, 2010

 

A Marked Point Process for Modeling Lidar Waveforms (paper)
Mallet C., Lafarge F., Roux M., Soergel U., Bretar F. and Heipke C.
IEEE Trans. on Image Processing, Vol. 19(12): pages 3204-3221, 2010

 

Hybrid Multi-view Reconstruction by Jump-Diffusion (paper, presentation)
 Lafarge F., Keriven R., Bredif M. and Vu, H.
Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, San Francisco, US, 2010

 

Insertion of 3D-Primitives in Mesh-Based Representations: Towards Compact Models Preserving the Details (paper)
Lafarge F., Keriven R. and Bredif M.
IEEE Trans. on Image Processing, Vol. 19(7): pages 1683-1694, 2010

 

Structural approach for building reconstruction from a single DSM (paper)
Lafarge F., Descombes X., Zerubia J. and Pierrot-Deseilligny M.
IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 32(1): pages 135-147, 2010