Efficient Edge-Aware Surface Mesh Reconstruction for Urban Scenes

András Bódis-Szomorú
Hayko Riemenschneider
Luc Van Gool

Journal of Computer Vision and Image Understanding (CVIU)
Special Issue on Large-Scale 3D Modeling of Urban Indoor or Outdoor Scenes from Images and Range Scans
April 2017


We propose an efficient approach for building compact, edge-preserving, view-centric triangle meshes from either dense or sparse depth data, with a focus on modeling architecture in large-scale urban scenes. Our method constructs a 2D base mesh from a preliminary view partitioning, then lifts the base mesh into 3D in a fast vertex depth optimization. Different view partitioning schemes are proposed for imagery and dense depth maps. They guarantee that mesh edges are aligned with crease edges and discontinuities. In particular, we introduce an effective plane merging procedure with a global error guarantee in order to maximally compact the resulting models. Moreover, different strategies for detecting and handling discontinuities are presented. We demonstrate that our approach provides an excellent trade-off between quality and compactness, and is eligible for fast production of polyhedral building models from large-scale urban height maps, as well as, for direct meshing of sparse street-side Structure-from-Motion (SfM) data.


  • Meshing approach for both street-side SfM data and large-scale urban height maps
  • Our meshes preserve crease edges and discontinuities without staircasing artifacts
  • 2D base mesh from superpixels or from piecewise-planar depth map partitioning
  • Fast linear vertex depth optimization including a curvature penalty term
  • Excellent trade-off between model compactness and approximation quality


Paper Preprint (26 pages)


author  =”Andr{\’a}s B{\’o}dis-Szomor{\’u} and Hayko Riemenschneider and Luc Van Gool”,
title =”Efficient edge-aware surface mesh reconstruction for urban scenes”,
journal = “Computer Vision and Image Understanding”,
volume  =”157″,
number  =””,
pages   =”3–24 “,
month   =”April”,
year    =”2017″,
issn    = “1077-3142”,
doi = “http://dx.doi.org/10.1016/j.cviu.2016.06.002”,