Florent Lafarge

University of Nice-Sophia Antipolis, Nice, Provence-Alpes-Côte d'Azur, France

Are you Florent Lafarge?

Claim your profile

Publications (39)31.43 Total impact

  • Graphical Models 09/2014; · 0.70 Impact Factor
  • Yannick Verdié, Florent Lafarge
    [Show abstract] [Hide abstract]
    ABSTRACT: Point processes constitute a natural extension of Markov random fields (MRF), designed to handle parametric objects. They have shown efficiency and competitiveness for tackling object extraction problems in vision. Simulating these stochastic models is however a difficult task. The performances of the existing samplers are limited in terms of computation time and convergence stability, especially on large scenes. We propose a new sampling procedure based on a Monte Carlo formalism. Our algorithm exploits the Markovian property of point processes to perform the sampling in parallel. This procedure is embedded into a data-driven mechanism so that the points are distributed in the scene in function of spatial information extracted from the input data. The performances of the sampler are analyzed through a set of experiments on various object detection problems from large scenes, including comparisons to the existing algorithms. The sampler is also tested as optimization algorithm for MRF-based labeling problems.
    International Journal of Computer Vision 01/2014; · 3.62 Impact Factor
  • Sven Oesau, Florent Lafarge, Pierre Alliez
    [Show abstract] [Hide abstract]
    ABSTRACT: We present a method for automatic reconstruction of permanent structures, such as walls, floors and ceilings, given a raw point cloud of an indoor scene. The main idea behind our approach is a graph-cut formulation to solve an inside/outside labeling of a space partitioning. We first partition the space in order to align the reconstructed models with permanent structures. The horizontal structures are located through analysis of the vertical point distribution, while vertical wall structures are detected through feature preserving multi-scale line fitting, followed by clustering in a Hough transform space. The final surface is extracted through a graph-cut formulation that trades faithfulness to measurement data for geometric complexity. A series of experiments show watertight surface meshes reconstructed from point clouds measured on multi-level buildings.
    ISPRS Journal of Photogrammetry and Remote Sensing 01/2014; 90:68–82. · 2.90 Impact Factor
  • Florent Lafarge, Pierre Alliez
    [Show abstract] [Hide abstract]
    ABSTRACT: We present a method for reconstructing surfaces from point sets. The main novelty lies in a structure-preserving approach where the input point set is first consolidated by structuring and resampling the planar components, before reconstructing the surface from both the consolidated components and the unstructured points. The final surface is obtained through solving a graph-cut problem formulated on the 3D Delaunay triangulation of the structured point set where the tetrahedra are labeled as inside or outside cells. Structuring facilitates the surface reconstruction as the point set is substantially reduced and the points are enriched with structural meaning related to adjacency between primitives. Our approach departs from the common dichotomy between smooth/piecewise-smooth and primitive-based representations by gracefully combining canonical parts from detected primitives and free-form parts of the inferred shape. Our experiments on a variety of inputs illustrate the potential of our approach in terms of robustness, flexibility and efficiency.
    Computer Graphics Forum 05/2013; 32(2pt2). · 1.64 Impact Factor
  • Yannick Verdié, Florent Lafarge
    [Show abstract] [Hide abstract]
    ABSTRACT: Point processes have demonstrated efficiency and competitiveness when addressing object recognition problems in vision. However, simulating these mathematical models is a difficult task, especially on large scenes. Existing samplers suffer from average performances in terms of computation time and stability. We propose a new sampling procedure based on a Monte Carlo formalism. Our algorithm exploits Markovian properties of point processes to perform the sampling in parallel. This procedure is embedded into a data-driven mechanism such that the points are non-uniformly distributed in the scene. The performances of the sampler are analyzed through a set of experiments on various object recognition problems from large scenes, and through comparisons to the existing algorithms.
    Proceedings of the 12th European conference on Computer Vision - Volume Part III; 10/2012
  • Source
    Florent Lafarge, Clément Mallet
    [Show abstract] [Hide abstract]
    ABSTRACT: We present a novel and robust method for modeling cities from 3D-point data. Our algorithm provides a more complete description than existing approaches by reconstructing simultaneously buildings, trees and topologically complex grounds. A major contribution of our work is the original way of modeling buildings which guarantees a high generalization level while having semantized and compact representations. Geometric 3D-primitives such as planes, cylinders, spheres or cones describe regular roof sections, and are combined with mesh-patches that represent irregular roof components. The various urban components interact through a non-convex energy minimization problem in which they are propagated under arrangement constraints over a planimetric map. Our approach is experimentally validated on complex buildings and large urban scenes of millions of points, and is compared to state-of-the-art methods.
    International Journal of Computer Vision 08/2012; 99(1). · 3.62 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: We present an original multi-view stereo reconstruction algorithm which allows the 3D-modeling of urban scenes as a combination of meshes and geometric primitives. The method provides a compact model while preserving details: irregular elements such as statues and ornaments are described by meshes whereas regular structures such as columns and walls are described by primitives (planes, spheres, cylinders, cones and tori). We adopt a two-step strategy consisting first in segmenting the initial mesh-based surface using a multi-label Markov Random Field based model and second, in sampling primitive and mesh components simultaneously on the obtained partition by a Jump-Diffusion process. The quality of a reconstruction is measured by a multi-object energy model which takes into account both photo-consistency and semantic considerations (i.e. geometry and shape layout). The segmentation and sampling steps are embedded into an iterative refinement procedure which provides an increasingly accurate hybrid representation. Experimental results on complex urban structures and large scenes are presented and compared to the state-of-the-art multi-view stereo meshing algorithms.
    IEEE Transactions on Software Engineering 04/2012; · 2.59 Impact Factor
  • Source
    Florent Lafarge, Clément Mallet
    [Show abstract] [Hide abstract]
    ABSTRACT: We present a robust method for modeling cities from unstructured point data. Our algorithm provides a more complete description than existing approaches by reconstructing simultaneously buildings, trees and topologically complex grounds. Buildings are modeled by an original approach which guarantees a high generalization level while having semantized and compact representations. Geometric 3D-primitives such as planes, cylinders, spheres or cones describe regular roof sections, and are combined with mesh-patches that represent irregular roof components. The various urban components interact through a non-convex energy minimization problem in which they are propagated under arrangement constraints over a planimetric map. We experimentally validate the approach on complex urban structures and large urban scenes of millions of points.
    IEEE International Conference on Computer Vision, ICCV 2011, Barcelona, Spain, November 6-13, 2011; 01/2011
  • Source
    Yannick Verdie, Florent Lafarge, Josiane Zerubia
    [Show abstract] [Hide abstract]
    ABSTRACT: We present an automatic approach for modeling buildings from aerial LiDAR data. The method produces accurate, watertight and compact meshes under planar constraints which are especially designed for urban scenes. The LiDAR point cloud is classified through a non-convex energy minimization problem in order to separate the points labeled as building. Roof structures are then extracted from this point subset, and used to control the meshing procedure. Experiments highlight the potential of our method in term of minimal rendering, accuracy and compactness.
    18th IEEE International Conference on Image Processing, ICIP 2011, Brussels, Belgium, September 11-14, 2011; 01/2011
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Lidar waveforms are 1-D signals representing a train of echoes caused by reflections at different targets. Modeling these echoes with the appropriate parametric function is useful to retrieve information about the physical characteristics of the targets. This paper presents a new probabilistic model based upon a marked point process which reconstructs the echoes from recorded discrete waveforms as a sequence of parametric curves. Such an approach allows to fit each mode of a waveform with the most suitable function and to deal with both, symmetric and asymmetric, echoes. The model takes into account a data term, which measures the coherence between the models and the waveforms, and a regularization term, which introduces prior knowledge on the reconstructed signal. The exploration of the associated configuration space is performed by a reversible jump Markov chain Monte Carlo (RJMCMC) sampler coupled with simulated annealing. Experiments with different kinds of lidar signals, especially from urban scenes, show the high potential of the proposed approach. To further demonstrate the advantages of the suggested method, actual laser scans are classified and the results are reported.
    IEEE Transactions on Image Processing 12/2010; 19(12):3204-21. · 3.20 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a new stochastic marked point process for describing images in terms of a finite library of geometric objects. Image analysis based on conventional marked point processes has already produced convincing results but at the expense of parameter tuning, computing time, and model specificity. Our more general multimarked point process has simpler parametric setting, yields notably shorter computing times, and can be applied to a variety of applications. Both linear and areal primitives extracted from a library of geometric objects are matched to a given image using a probabilistic Gibbs model, and a Jump-Diffusion process is performed to search for the optimal object configuration. Experiments with remotely sensed images and natural textures show that the proposed approach has good potential. We conclude with a discussion about the insertion of more complex object interactions in the model by studying the compromise between model complexity and efficiency.
    IEEE Transactions on Software Engineering 09/2010; 32(9):1597-609. · 2.59 Impact Factor
  • F. Lafarge, R. Keriven, M. Brédif
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose an original hybrid modeling process of urban scenes that represents 3-D models as a combination of mesh-based surfaces and geometric 3-D-primitives. Meshes describe details such as ornaments and statues, whereas 3-D-primitives code for regular shapes such as walls and columns. Starting from an 3-D-surface obtained by multiview stereo techniques, these primitives are inserted into the surface after being detected. This strategy allows the introduction of semantic knowledge, the simplification of the modeling, and even correction of errors generated by the acquisition process. We design a hierarchical approach exploring different scales of an observed scene. Each level consists first in segmenting the surface using a multilabel energy model optimized by -expansion and then in fitting 3-D-primitives such as planes, cylinders or tori on the obtained partition where relevant. Experiments on real meshes, depth maps and synthetic surfaces show good potential for the proposed approach.
    IEEE Transactions on Image Processing 08/2010; · 3.20 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: We propose a multi-view stereo reconstruction algorithm which recovers urban scenes as a combination of meshes and geometric primitives. It provides a compact model while preserving details: irregular elements such as statues and ornaments are described by meshes whereas regular structures such as columns and walls are described by primitives (planes, spheres, cylinders, cones and tori). A Jump-Diffusion process is designed to sample these two types of elements simultaneously. The quality of a reconstruction is measured by a multi-object energy model which takes into account both photo-consistency and semantic considerations (i.e. geometry and shape layout). The sampler is embedded into an iterative refinement procedure which provides an increasingly accurate hybrid representation. Experimental results on complex urban structures and large scenes are presented and compared to multi-view based meshing algorithms.
    The Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010, San Francisco, CA, USA, 13-18 June 2010; 01/2010
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We present a new approach for building reconstruction from a single Digital Surface Model (DSM). It treats buildings as an assemblage of simple urban structures extracted from a library of 3D parametric blocks (like a LEGO set). First, the 2D-supports of the urban structures are extracted either interactively or automatically. Then, 3D-blocks are placed on the 2D-supports using a Gibbs model which controls both the block assemblage and the fitting to data. A Bayesian decision finds the optimal configuration of 3D-blocks using a Markov Chain Monte Carlo sampler associated with original proposition kernels. This method has been validated on multiple data set in a wide-resolution interval such as 0.7 m satellite and 0.1 m aerial DSMs, and provides 3D representations on complex buildings and dense urban areas with various levels of detail.
    IEEE Transactions on Software Engineering 01/2010; 32(1):135-47. · 2.59 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Lidar waveforms are 1D signal consisting of a train of echoes where each of them correspond to a scattering target of the Earth surface. Modeling these echoes with the appropriate parametric function is necessary to retrieve physical information about these objects and characterize their properties. This paper presents a marked point process based model to reconstruct a lidar signal in terms of a set of parametric functions. The model takes into account both a data term which measures the coherence between the models and the waveforms, and a regularizing term which introduces physical knowledge on the reconstructed signal. We search for the best configuration of functions by performing a Reversible Jump Markov Chain Monte Carlo sampler coupled with a simulated annealing. Results are finally presented on different kinds of signals in urban areas.
    Image Processing (ICIP), 2009 16th IEEE International Conference on; 12/2009
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In contrast to conventional airborne multi-echo laser scanner systems, full-waveform (FW) lidar systems are able to record the entire emitted and backscattered signals of each laser pulse. Instead of clouds of individual 3D points, FW devices provide 1D profiles of the 3D scene, which allows gaining additional and more detailed observations of the illuminated surfaces. Indeed, lidar waveforms are signals consisting of a train of echoes where each of them corresponds to a scattering target of the Earth surface or a group of close objects leading to superimposed signals. Modelling these echoes with the appropriate parametric function is necessary to retrieve physical information about these objects and characterize their properties. Henceforth, the extracted parameters can be useful for subsequent object segmentation and/or classification. This paper presents a stochastic based model to reconstruct lidar waveforms in terms of a set of parametric functions. The model takes into account both a data term which measures the coherence between the proposed configurations and the waveforms, and a regularizing term which introduces physical knowledge on the reconstructed signal. We search for the best configuration of functions by performing a Reversible Jump Markov Chain Monte Carlo sampler coupled with a stochastic relaxation. Finally, the algorithm is validated on waveforms from several airborne lidar sensors, showing the suitability of the approach even when the traditional assumption of Gaussian decomposition of waveforms is invalid.
    International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences (IAPRS); 09/2009
  • Source
    Florent Lafarge, Renaud Keriven, Mathieu Brédif
    British Machine Vision Conference, BMVC 2009, London, UK, September 7-10, 2009. Proceedings; 01/2009
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present an automatic building extraction method from Digital Elevation Models based on an object approach. First, a rough approximation of the building footprints is realized by a method based on marked point processes: the building footprints are modeled by rectangle layouts. Then, these rectangular footprints are regularized by improving the connection between the neighboring rectangles and detecting the roof height discontinuities. The obtained building footprints are structured footprints: each element represents a specific part of an urban structure. Results are finally applied to a 3D-city modeling process.
    ISPRS Journal of Photogrammetry and Remote Sensing. 01/2008;
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a new approach to describe images in terms of geometric objects. Methods based on conventional stochastic marked point processes have already led to convincing image analysis results but possess several drawbacks such as complex parameter tuning, large computing time, and lack of generality. We propose a generalized marked point process model which can be performed in shorter computing times and applied to a variety of applications without modifying the model or tuning parameters. In our approach, both linear and areal primitives extracted from a library of geometric objects are matched to a given image using a probabilistic Gibbs model. A Jump-Diffusion process is performed to find the optimal object configuration. Experiments with remotely sensed images show good potentialities of the proposed approach.
    Advanced Concepts for Intelligent Vision Systems, 10th International Conference, ACIVS 2008, Juan-les-Pins, France, October 20-24, 2008. Proceedings; 01/2008
  • Source
    Florent Lafarge, Georgy L. Gimel'farb
    [Show abstract] [Hide abstract]
    ABSTRACT: Our goal is to represent images in terms of geometric objects acting as prim- itive elements of an image description. Similar representations obtained by stochastic marked point processes have already led to convincing image anal- ysis results but suffer from serious drawbacks such as complex and unstable parameter tuning, large computing time, and lack of generality. We propose an alternative descriptive model based on a Jump-Diffusion process which can be performed in shorter computing times and applied to a variety of ap- plications without changing the model or modifying the tuning parameters. In our approach, a probabilistic Gibbs model is adapted to a library of geo- metric objects and is sampled by a Jump-Diffusion process in order to closely match an underlying texture. Experiments with natural textures and remotely sensed images show good potentialities of the proposed approach1.
    Proceedings of the British Machine Vision Conference 2008, Leeds, September 2008; 01/2008

Publication Stats

170 Citations
31.43 Total Impact Points

Institutions

  • 2010–2013
    • University of Nice-Sophia Antipolis
      Nice, Provence-Alpes-Côte d'Azur, France
    • National Institute for Research in Computer Science and Control
      Le Chesney, Île-de-France, France
  • 2009
    • Université Paris-Est Marne-la-Vallée
      Champs, Île-de-France, France
    • University of Paris-Est
      Centre, France
  • 2008
    • University of Auckland
      • Department of Computer Science
      Окленд, Auckland, New Zealand