research-article

LOD Generation for Urban Scenes

Authors:

Yannick Verdie,

Florent Lafarge,

Pierre AlliezAuthors Info & Claims

ACM Transactions on Graphics (TOG), Volume 34, Issue 3

Article No.: 30, Pages 1 - 14

https://doi.org/10.1145/2732527

Published: 08 May 2015 Publication History

Abstract

We introduce a novel approach that reconstructs 3D urban scenes in the form of levels of detail (LODs). Starting from raw datasets such as surface meshes generated by multiview stereo systems, our algorithm proceeds in three main steps: classification, abstraction, and reconstruction. From geometric attributes and a set of semantic rules combined with a Markov random field, we classify the scene into four meaningful classes. The abstraction step detects and regularizes planar structures on buildings, fits icons on trees, roofs, and facades, and performs filtering and simplification for LOD generation. The abstracted data are then provided as input to the reconstruction step which generates watertight buildings through a min-cut formulation on a set of 3D arrangements. Our experiments on complex buildings and large-scale urban scenes show that our approach generates meaningful LODs while being robust and scalable. By combining semantic segmentation and abstraction, it also outperforms general mesh approximation approaches at preserving urban structures.

Supplementary Material

verdie (verdie.zip)

Supplemental movie, appendix, image and software files for, LOD Generation for Urban Scenes

Download
96.87 MB

MP4 File (a30.mp4)

Download
16.51 MB

References

[1]

Acute3D. 2014. http://www.acute3d.com/.

[2]

H. Arefi, J. Engels, M. Hahn, and H. Mayer. 2008. Levels of detail in 3D building reconstruction from LIDAR data. In Proceedings of the International Society for Photogrammetry and Remote Sensing Conference (ISPRS'08).

[3]

M. Arikan, M. Schwarzler, S. Flory, M. Wimmer, and S. Maierhofer. 2013. O-snap: Optimization-based snapping for modeling architecture. ACM Trans. Graph. 32, 1.

Digital Library

[4]

M. Attene, S. Katz, M. Mortara, G. Patane, M. Spagnuolo, and A. Tal. 2006. Mesh segmentation -- A comparative study. In Proceedings of the IEEE International Conference on Shape Modeling and Applications (SMI'06). 7.

Digital Library

[5]

Autodesk. 2014. http://www.123dapp.com/catch.

[6]

F. Bao, D.-M. Yan, N. Mitra, and P. Wonka. 2013. Generating and exploring good building layouts. ACM Trans. Graph. 32, 122:1--122:10.

Digital Library

[7]

Y. Boykov and V. Kolmogorov. 2004. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Trans. Pattern Anal. Mach. Intell. 26, 9.

Digital Library

[8]

Y. Boykov, O. Veksler, and R. Zabih. 2001. Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23, 11.

Digital Library

[9]

A.-L. Chauve, P. Labatut, and J.-P. Pons. 2010. Robust piecewise-planar 3D reconstruction and completion from large-scale unstructured point data. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'10).

[10]

X. Chen, A. Golovinskiy, and T. Funkhouser. 2009. A benchmark for 3D mesh segmentation. ACM Trans. Graph. 28, 3.

Digital Library

[11]

D. Cohen-Steiner, P. Alliez, and M. Desbrun. 2004. Variational shape approximation. ACM Trans. Graph. 23, 3, 905--914.

Digital Library

[12]

D. Cohen-Steiner and J.-M. Morvan. 2003. Restricted Delaunay triangulations and normal cycle. In Proceedings of the 19^th Annual Symposium on Computational Geometry (SCG'03). 312--321.

Digital Library

[13]

J. M. Coughlan and A. L. Yuille. 2000. The Manhattan world assumption: Regularities in scene statistics which enable Bayesian interference. In Proceedings of the Conference on Neural Information Processing Systems (NIPS'00).

[14]

B. Falcidieno and M. Spagnuolo. 1998. A shape abstraction paradigm for modeling geometry and semantics. In Proceedings of the Conference on Computer Graphics International (CGI'98). 646--656.

Digital Library

[15]

C. Frueh and A. Zakhor. 2003. Constructing 3D city models by merging ground-based and airborne views. In Proceedings of the IEEE Computer Science Conference on Computer Vision and Pattern Recognition (CVPR'03). 562--569.

[16]

Y. Furukawa, B. Curless, S. Seitz, and R. Szeliski. 2009. Manhattan-world stereo. In Proceedings of the IEEE Computer Science Conference on Computer Vision and Pattern Recognition (CVPR'09).

[17]

M. Garland and P. Heckbert. 1997. Surface simplification using quadric error metrics. In Proceedings of the 24^thAnnual ACM SIGGRAPH Conference on Computer Graphics and Interactive Techniques. 209--216.

Digital Library

[18]

G. Groger and L. Plumer. 2012. CityGML interoperable semantic 3D city models. J. Photogram. Remot. Sens. 71.

[19]

C. Haene, C. Zach, A. Cohen, R. Angst, and M. Pollefeys. 2013. Joint 3D scene reconstruction and class segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'13). 97--104.

Digital Library

[20]

T. Ju. 2004. Robust repair of polygonal models. In Proceedings of the ACM SIGGRAPH Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH'04). ACM Press, New York, 888--895.

Digital Library

[21]

E. Kalogerakis, A. Hertzmann, and K. Singh. 2010. Learning 3D mesh segmentation and labeling. ACM Trans. Graph. 29, 4.

Digital Library

[22]

F. Lafarge and P. Alliez. 2013. Surface reconstruction through point set structuring. Comput. Graph. Forum 32, 2.

[23]

F. Lafarge, X. Descombes, J. Zerubia, and M. Pierrot-Deseilligny. 2010. Structural approach for building reconstruction from a single DSM. IEEE Trans. Pattern Anal. Mach. Intell. 32, 1.

Digital Library

[24]

F. Lafarge and C. Mallet. 2012. Creating large-scale city models from 3D-point clouds: A robust approach with hybrid representation. Int. J. Comput. Vis. 99, 1.

Digital Library

[25]

F. Leberl, A. Irschara, T. Pock, P. Meixner, M. Gruber, S. Scholz, and A. Wiechert. 2010. Point clouds: LIDAR versus 3D vision. Photogram. Engin. Remot. Sens. 76, 10.

[26]

S. Z. Li. 2001. Markov Random Field Modeling in Image Analysis. Springer.

[27]

Y. Li, X. Wu, Y. Chrysathou, A. Sharf, R. D. Cohen, and N. J. Mitra. 2011. Globfit: Consistently fitting primitives by discovering global relations. ACM Trans. Graph. 30, 4.

Digital Library

[28]

H. Lin, J. Gao, Y. Zhou, G. Lu, M. Ye, C. Zhang, L. Liu, and R. Yang. 2013. Semantic decomposition and reconstruction of residential scenes from LIDAR data. ACM Trans. Graph. 32, 4.

Digital Library

[29]

D. Luebke, B. Watson, J. D. Cohen, M. Reddy, and A. Varshney. 2002. Level of Detail for 3D Graphics, Morgan Kaufmann, San Francisco.

Digital Library

[30]

A. Martinovic, M. Mathias, J. Weissenberg, and L. Van Gool. 2012. A three-layered approach to façcade parsing. In Proceedings of the 12^th European Conference on Computer Vision (ECCV'12). 416--429.

Digital Library

[31]

R. Mehra, Q. Zhou, J. Long, A. Sheffer, A. Gooch, and N. Mitra. 2009. Abstraction of man-made shapes. ACM Trans. Graph. 28, 5.

Digital Library

[32]

N. Mitra, M. Wand, H. Zhang, D. Cohen-Or, and M. Bokeloh. 2013. Structure-aware shape processing. In EUROGRAPHICS State-of-the-Art Report.

[33]

P. Muslalski, P. Wonka, D. Aliaga, M. Wimmer, L. Van Gool, and W. Purgathofer. 2013. A survey of urban reconstruction. Comput. Graph. Forum 32, 6.

Digital Library

[34]

S. Oesau, F. Lafarge, and P. Alliez. 2014. Indoor scene reconstruction using feature sensitive primitive extraction and graph-cut. ISPRS J. Photogram. Remot. Sens. 90.

[35]

M. Pauly, M. H. Gross, and L. Kobbelt. 2002. Efficient simplification of point-sampled surfaces. ACM Trans. Graph. 21, 3, 322--329.

[36]

Pix4D. 2014. http://pix4d.com/.

[37]

C. Poullis and S. You. 2009. Automatic reconstruction of cities from remote sensor data. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'09). 2775--2782.

[38]

H. Riemenschneider, U. Krispel, W. Thaller, M. Donoser, S. Havemann, D. Fellner, and H. Bischof. 2012. Irregular latencies for complex shape grammar façcade parsing. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'12).

Digital Library

[39]

F. Rottensteiner, G. Sohn, J. Jung, M. Gerke, C. Baillard, S. Benitez, and U. Breitkopf. 2012. The ISPRS benchmark on urban object classification and 3D building reconstruction. In Proceedings of the International Society for Photogrammetry and Remote Sensing Congress (ISPRS'12).

[40]

A. Shamir. 2008. A survey on mesh segmentation techniques. Comput. Graph. Forum 27, 6.

[41]

S. Sinha, D. Steedly, R. Szeliski, M. Agrawala, and M. Pollefeys. 2008. Interactive 3D architectural modeling from unordered photo collections. ACM Trans. Graph. 27, 5.

Digital Library

[42]

O. Teboul, L. Simon, P. Koutsourakis, and N. Paragios. 2010. Segmentation of building facades using procedural shape prior. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'10). 3105--3112.

[43]

A. Toshev, P. Mordohai, and B. Taskar. 2010. Detecting and parsing architecture at city scale from range data. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'10).

[44]

C. Vanegas, D. Aliaga, and B. Benes. 2010a. Building reconstruction using Manhattan-world grammars. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'10).

[45]

C. Vanegas, D. Aliaga, P. Wonka, P. Muller, P. Waddell, and B. Watson. 2010b. Modeling the appearance and behavior of urban spaces. In EUROGRAPHICS State-of-the-Art Report.

[46]

C. Vanegas, D. Aliaga, and B. Benes. 2012. Automatic extraction of Manhattan-world building masses from 3D laser range scans. IEEE Trans. Visual. Comput. Graph. 18, 10.

Digital Library

[47]

Y. Verdie and F. Lafarge. 2014. Detecting parametric objects in large scenes by Monte Carlo sampling. Int. J. Comput. Vis. 106, 1.

Digital Library

[48]

M. E. Yumer and L. B. Kara. 2012. Co-abstraction of shape collections. ACM Trans. Graph. 31, 6.

Digital Library

[49]

L. Zebedin, J. Bauer, K. Karner, and H. Bischof. 2008. Fusion of feature- and area-based information for urban building modeling from aerial imagery. In Proceedings of the European Conference on Computer Vision (ECCV'08).

Digital Library

[50]

K. Zhou, E. Zhang, J. Bittner, and P. Wonka. 2008. Visibility-driven mesh analysis and visualization through graph cuts. IEEE Trans. Visual. Comput. Graph. 14, 6.

Digital Library

[51]

Q. Zhou and U. Neumann. 2012. 2.5D building modeling by discovering global regularities. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'12).

Digital Library

Cited By

DONG MXIE KHUANG H(2024)Coupled study on instance segmentation and structural reconstruction of buildings in 3D urban scenesSCIENTIA SINICA Informationis10.1360/SSI-2023-0221Online publication date: 7-Feb-2024
https://doi.org/10.1360/SSI-2023-0221
Shao JYao WWang PHe ZLuo L(2024)Urban GeoBIM Construction by Integrating Semantic LiDAR Point Clouds With as-Designed BIM ModelsIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2024.335837062(1-12)Online publication date: 2024
https://doi.org/10.1109/TGRS.2024.3358370
Wang LHu HShang QZeng HZhu Q(2024)StructuredMesh: 3-D Structured Optimization of Façade Components on Photogrammetric Mesh Models Using Binary Integer ProgrammingIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2023.334849262(1-12)Online publication date: 2024
https://doi.org/10.1109/TGRS.2023.3348492
Show More Cited By

Index Terms

LOD Generation for Urban Scenes
1. Computing methodologies
  1. Computer graphics
    1. Shape modeling
2. Theory of computation
  1. Randomness, geometry and discrete structures
    1. Computational geometry

Recommendations

Large Scale Urban Scene Modeling from MVS Meshes
Computer Vision – ECCV 2018
Abstract
In this paper we present an efficient modeling framework for large scale urban scenes. Taking surface meshes derived from multi-view-stereo systems as input, our algorithm outputs simplified models with semantics at different levels of detail (...
Reconstructing building mass models from UAV images

We present an automatic reconstruction pipeline for large scale urban scenes from aerial images captured by a camera mounted on an unmanned aerial vehicle. Using state-of-the-art Structure from Motion and Multi-View Stereo algorithms, we first generate ...
A Survey of Urban Reconstruction

This paper provides a comprehensive overview of urban reconstruction. While there exists a considerable body of literature, this topic is still under active research. The work reviewed in this survey stems from the following three research communities: ...

Comments

Information & Contributors

Information

Published In

cover image ACM Transactions on Graphics

ACM Transactions on Graphics Volume 34, Issue 3

April 2015

152 pages

ISSN:0730-0301

EISSN:1557-7368

DOI:10.1145/2774971

Editor:
Kavita Bala
Cornell University

Issue’s Table of Contents

Copyright © 2015 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 08 May 2015

Accepted: 01 February 2015

Revised: 01 December 2014

Received: 01 April 2014

Published in TOG Volume 34, Issue 3

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed

Funding Sources

ERC Starting Grant "Robust Geometry Processing" (257474)

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

120
Total Citations
View Citations
999
Total Downloads

Downloads (Last 12 months)62
Downloads (Last 6 weeks)9

Reflects downloads up to 14 Aug 2024

Other Metrics

View Author Metrics

Citations

Cited By

DONG MXIE KHUANG H(2024)Coupled study on instance segmentation and structural reconstruction of buildings in 3D urban scenesSCIENTIA SINICA Informationis10.1360/SSI-2023-0221Online publication date: 7-Feb-2024
https://doi.org/10.1360/SSI-2023-0221
Shao JYao WWang PHe ZLuo L(2024)Urban GeoBIM Construction by Integrating Semantic LiDAR Point Clouds With as-Designed BIM ModelsIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2024.335837062(1-12)Online publication date: 2024
https://doi.org/10.1109/TGRS.2024.3358370
Wang LHu HShang QZeng HZhu Q(2024)StructuredMesh: 3-D Structured Optimization of Façade Components on Photogrammetric Mesh Models Using Binary Integer ProgrammingIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2023.334849262(1-12)Online publication date: 2024
https://doi.org/10.1109/TGRS.2023.3348492
Liu XLiu ZZhang YGao ZTan Y(2024) UMeshSegNet: Semantic Segmentation of 3D Mesh Generated from UAV Photogrammetry * 2024 IEEE 18th International Conference on Control & Automation (ICCA)10.1109/ICCA62789.2024.10591843(388-393)Online publication date: 18-Jun-2024
https://doi.org/10.1109/ICCA62789.2024.10591843
Arhrib YEl Kharki OWahbi MAlaoui OMaatouk MBoulaassal H(2024)The road toward smart city infrastructures: A review on 3d facade reconstruction using imagesE3S Web of Conferences10.1051/e3sconf/202450202007502(02007)Online publication date: 11-Mar-2024
https://doi.org/10.1051/e3sconf/202450202007
Liu YObukhov AWegner JSchindler K(2024)Point2Building: Reconstructing buildings from airborne LiDAR point cloudsISPRS Journal of Photogrammetry and Remote Sensing10.1016/j.isprsjprs.2024.07.012215(351-368)Online publication date: Sep-2024
https://doi.org/10.1016/j.isprsjprs.2024.07.012
Wu YXue FLi MChen S(2024)A novel Building Section Skeleton for compact 3D reconstruction from point clouds: A study of high-density urban scenesISPRS Journal of Photogrammetry and Remote Sensing10.1016/j.isprsjprs.2024.01.020209(85-100)Online publication date: Mar-2024
https://doi.org/10.1016/j.isprsjprs.2024.01.020
Romanengo CFalcidieno BBiasotti S(2024)From aerial LiDAR point clouds to multiscale urban representation levels by a parametric resamplingComputers & Graphics10.1016/j.cag.2024.104022123(104022)Online publication date: Oct-2024
https://doi.org/10.1016/j.cag.2024.104022
Xiang XJiang HYu YShen DZhen JBao HZhou XZhang G(2024)Efficient High-Quality Vectorized Modeling of Large-Scale ScenesInternational Journal of Computer Vision10.1007/s11263-024-02059-xOnline publication date: 20-May-2024
https://doi.org/10.1007/s11263-024-02059-x
Ma RChen JYang CLi X(2024)A Method for Semantic City ModelingProceedings of the 3rd International Civil Engineering and Architecture Conference10.1007/978-981-99-6368-3_73(903-912)Online publication date: 6-Feb-2024
https://doi.org/10.1007/978-981-99-6368-3_73
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Issue’s Table of Contents