Adaptive Partitioning of Urban Facades

Figure: Given input unorganized point clouds of 3D urban facades, a recursive adaptive partitioning is automatically performed to build a hierarchy of building blocks upon them (from left to right). The splitting direction, number and location of splitting planes are all adaptively determined in each step. Repetitive patterns are indicated by different colors.

Automatically discovering high-level facade structures in unorganized 3D point clouds of urban scenes is crucial for gigantic applications like digitalization of real cities. However, this problem is challenging due to poor-quality input data, contaminated with severe missing areas, noise and outliers. This work introduces the concept of adaptive partitioning to automatically derive a flexible and hierarchical representation of 3D urban facades. Our key observation is that urban facades are largely governed by concatenated and/or interlaced grids. Hence, unlike previous automatic facade analysis works which are restricted to globally rectilinear grids, we propose to automatically partition the facade in an adaptive manner, in which the splitting direction, the number and location of splitting planes are all adaptively determined. Such an adaptive partition operation is performed recursively to generate a hierarchical representation of the facade. We show that the concept of adaptive partitioning is also applicable to flexible and robust analysis of image facades. We evaluate our method on a dozen of LiDAR scans of various complexity and styles, and the image facades from the eTRIMS database and the Ecole Centrale Paris database. A series of applications that benefit from our approach are also demonstrated.

Adaptive Partitioning of Urban Facades [Paper (4.1M)]

Chao-Hui Shen, Shi-Sheng Huang, Hongbo Fu, and Shi-Min Hu.

ACM Transactions on Graphics (SIGGRAPH ASIA 2011), 30(6), 184:1-184:9

@article {shen2011adaptive,
  author = {Shen, Chao-Hui and Huang, Shi-Sheng and Fu, Hongbo and Hu, Shi-Min},
  title = {Adaptive Partitioning of Urban Facades},
  journal = {ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH ASIA 2011},
  year = {2011}
  volume = {30}
  number = {6}
  pages = {184:1-184:9}
}

Adaptive partitioning of unorganized 3D point clouds:

Adaptive partitioning of image facades:

[Supplementary Material 1 (13.0M)] additional 3D examples

[Supplementary Material 2 (11.9M)] results on the eTRIMS Image Database

[Supplementary Material 3 (9.1M)] some intermediate results

[Supplementary Material 4 (5.1M)] representative results on the CVPR 2010 data set in the Ecole Centrale Paris Database; click here to see more results

[Presentation Slides (40.1M)]

We thank the anonymous reviewers for their constructive comments. The LiDAR scans in Figure 1(b), Figure 7(c)(f) and Figure 12 are courtesy of the Institute of Cartography and Geoinformatics, Leibniz University at Hannover. The rest of the LiDAR scans in the paper are courtesy of Professor Baoquan Chen at Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences. Shi-Min Hu is supported by the National Basic Research Project of China (Project Number 2011CB302203), the Natural Science Foundation of China (Project Number 61120106007). Hongbo Fu is partly supported by grants from CityU (Project Number SRG7002533), and the HKSAR Research Grants Council (Project Number 9041562).