BigSUR: Large-scale Structured Urban Reconstruction (SIGGRAPH Asia 2017)

BigSUR: Large-scale Structured Urban Reconstruction (SIGGRAPH Asia 2017) from SmartGeometry on YouTube.

Description

The creation of high quality semantically parsed 3D models for dense metropolitan areas is a fundamental problem in urban modeling. Although recent advances in acquisition techniques and processing algorithms have resulted in large scale imagery or 3D polygonal reconstructions, such data-sources are typically noisy, incomplete, and have no semantic structure. In this paper, we present an automatic data fusion technique that produces high quality structured models of city blocks. Starting from coarse polygonal meshes, street-level imagery, and GIS footprints, we formulate a binary integer program which globally balances different sources of error to produce semantically parsed mass models with associated façade elements. We demonstrate our system on regions of four different cities of varying complexity; our typical examples contain densely built urban blocks spanning hundreds of buildings.

References

Kelly, T., Femiani, J., Wonka, P., & Mitra, N. J. (2017). BigSUR: large-scale structured urban reconstruction. ACM Transactions on Graphics, 36(6).

Website

BigSUR: Large-scale Structured Urban Reconstruction: http://geometry.cs.ucl.ac.uk/projects/2017/bigsur/