Template Assembly for Detailed Urban Reconstruction

Liangliang Nan KAUST, KSA Caigui Jiang KAUST, KSA Bernard Ghanem KAUST, KSA Peter Wonka KAUST, KSA

Geometric Modeling and Processing mathscidoc:1608.16111

Eurographics / Computer Graphics Forum, 34, (2), 2015
We propose a new framework to reconstruct building details by automatically assembling 3D templates on coarse textured building models. In a preprocessing step, we generate an initial coarse model to approximate a point cloud computed using Structure from Motion and Multi View Stereo, and we model a set of 3D templates of facade details. Next, we optimize the initial coarse model to enforce consistency between geometry and appearance (texture images). Then, building details are reconstructed by assembling templates on the textured faces of the coarse model. The 3D templates are automatically chosen and located by our optimization-based template assembly algorithm that balances image matching and structural regularity. In the results, we demonstrate how our framework can enrich the details of coarse models using various data sets.
template assembly, urban reconstruction, point cloud, template matching, optimization
[ Download ] [ 2016-08-29 14:16:35 uploaded by liangliangnan ] [ 402 downloads ] [ 0 comments ]
  title={Template Assembly for Detailed Urban Reconstruction},
  author={Liangliang Nan, Caigui Jiang, Bernard Ghanem, and Peter Wonka},
  booktitle={Eurographics / Computer Graphics Forum},
Liangliang Nan, Caigui Jiang, Bernard Ghanem, and Peter Wonka. Template Assembly for Detailed Urban Reconstruction. 2015. Vol. 34. In Eurographics / Computer Graphics Forum. http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20160829141635860198538.
Please log in for comment!
Contact us: office-iccm@tsinghua.edu.cn | Copyright Reserved