CGI 2016 – Coarse-to-fine model fitting on point cloud

Reema Bajwa, Syed Rizwan Gilani, Murtaza Taj

Short Paper Proceedings of the 33rd Computer Graphics International, Heraklion, Greece, June 28 – July 1, 2016

Abstract

We present a coarse-to-fine model fitting approach that automatically generates a detailed CAD like model from a point cloud. We first developed a library of detailed parametric models for each of the architectural elements. The parameter estimate of these models is obtained using an efficient 3D shape fitting and peak finding approach that operates on the planar and 1D projections of the point clouds. The approach performs coarse-to-fine segmentation that reveals intrinsic details resulting in efficient and accurate parameter estimation. As compared to coarse fitting, our method significantly increases the amount of details in the recovered 3D model.

Resources

Download PDF
(Distributed here for timely dissemination of scholarly work. Copyright retained by copyright holders. May not be posted without permission from copyright holders.)

Text Reference:

Reema Bajwa, Syed Rizwan Gilani, Murtaza Taj, 
"3D Architectural Modeling: Coarse-to-fine model fitting on point cloud", 
in Proceedings of the 33rd Computer Graphics International, CGI, 
June 2016 (short paper)

Bibtex Reference:

@inproceedings{Coarse2FineCGI2016,
   author   = "Reema Bajwa and
               Syed Rizwan Gilani and              
               Murtaza Taj",
   title     = "3{D} Architectural Modeling: Coarse-to-fine model fitting on point cloud",
   booktitle = "Proceedings of the 33rd Computer Graphics International",
   month     = "June",
   year      = "2016",
}