This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
A Hybrid Multiview Stereo Algorithm for Modeling Urban Scenes
Jan. 2013 (vol. 35 no. 1)
pp. 5-17
F. Lafarge, Geometrica Res. Group, INRIA Sophia Antipolis, Sophia Antipolis, France
R. Keriven, Acute3D, Sophia Antipolis, France
M. Brédif, Matis Lab., Univ. Paris Est, St. Mande, France
Hoang-Hiep Vu, Imagine Group, Univ. Paris Est, Marne la Vallee, France
We present an original multiview 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 multilabel 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 state-of-the-art multiview stereo meshing algorithms.
Index Terms:
stereo image processing,image reconstruction,image sampling,image segmentation,iterative methods,Markov processes,solid modelling,hybrid multiview stereo reconstruction algorithm,3D urban scene modeling,iterative refinement procedure,shape layout,photo-consistency,multiobject energy model,reconstruction quality,jump-diffusion process,mesh component sampling,primitive component sampling,multilabel Markov random field-based model,mesh-based surface segmentation,two-step strategy,tori primitive,cone primitive,cylinder primitive,sphere primitive,planes primitive,walls,columns,regular structures,ornaments,statues,irregular elements,detail preservation,geometric primitives,Image reconstruction,Three dimensional displays,Shape,Adaptation models,Semantics,Stereo image processing,jump-diffusion,3D modeling,multiview stereo,urban scenes,hybrid representation
Citation:
F. Lafarge, R. Keriven, M. Brédif, Hoang-Hiep Vu, "A Hybrid Multiview Stereo Algorithm for Modeling Urban Scenes," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 1, pp. 5-17, Jan. 2013, doi:10.1109/TPAMI.2012.84
Usage of this product signifies your acceptance of the Terms of Use.