Global, Dense Multiscale Reconstruction
for a Billion Points

Abstract

We present a variational approach for surface reconstruction from a set of oriented points with scale information. We focus particularly on scenarios with non-uniform point densities due to images taken from different distances. In contrast to previous methods, we integrate the scale information in the objective and globally optimize the signed distance function of the surface on a balanced octree grid. We use a finite element discretization on the dual structure of the octree minimizing the number of variables. The tetrahedral mesh is generated efficiently from the dual structure, and also memory efficiency is optimized, such that robust data terms can be used even on very large scenes. The surface normals are explicitly optimized and used for surface extraction to improve the reconstruction at edges and corners.


Downloads
descriptionPaper  file_downloadSoftware Linux 64bit file_downloadBreisach Dataset
Videos

ICCV video spotlight

Citywall data set

The citywall data set is part of the Multi View Environment from TU Darmstadt and can be obtained here.

References

If you use our software, please cite the following paper(s):

B. Ummenhofer and T. Brox, "Global, Dense Multiscale Reconstruction for a Billion Points", Int J Comput Vis, pp. 1--13, Jun. 2017.[doi] [BibTex]

B.Ummenhofer and T.Brox: "Global, Dense Multiscale Reconstruction for a Billion Points", in 2015 IEEE International Conference on Computer Vision (ICCV), 2015. [BibTex]