Large Scale Urban Scene Modeling from MVS Meshes
Pages 640 - 655
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 (LODs). Our key observation is that urban building is usually composed of planar roof tops connected with vertical walls. There are two major steps in our framework: segmentation and building modeling. The scene is first segmented into four classes with a Markov random field combining height and image features. In the following modeling step, various 2D line segments sketching the roof boundaries are detected and slice the plane into faces. Through assigning each face with a roof plane, the final model is constructed by extruding the faces to the corresponding planes. By combining geometric and appearance cues together, the proposed method is robust and fast compared to the state-of-the-art algorithms.
References
[1]
Acute3D: Acute3D. https://www.acute3d.com/
[2]
Agarwal S et al. Building Rome in a day Commun. ACM 2011 54 10 105-112
[3]
Boykov Y and Kolmogorov V An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision IEEE Trans. Pattern Anal. Mach. Intell. 2004 26 9 1124-1137
[4]
Boykov Y, Veksler O, and Zabih R Fast approximate energy minimization via graph cuts IEEE Trans. Pattern Anal. Mach. Intell. 2001 23 11 1222-1239
[5]
Chong, H.Y., Gortler, S.J., Zickler, T.: A perception-based color space for illumination-invariant image processing. In: ACM SIGGRAPH, pp. 61:1–61:7 (2008)
[6]
CityGML: CityGML. http://www.opengeospatial.org/standards/citygml
[7]
Cohen-Steiner, D., Alliez, P., Desbrun, M.: Variational shape approximation. In: ACM SIGGRAPH, pp. 905–914 (2004)
[8]
Cui, H., Gao, X., Shen, S., Hu, Z.: HSfM: hybrid structure-from-motion. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2393–2402 (2017)
[9]
Cui H, Shen S, Gao W, and Hu Z Efficient large-scale structure from motion by fusing auxiliary imaging information IEEE Trans. Image Process. 2015 22 11 3561-3573
[10]
Freund Y and Schapire RE A decision-theoretic generalization of on-line learning and an application to boosting J. Comput. Syst. Sci. 1997 55 1 119-139
[11]
Furukawa, Y., Curless, B., Seitz, S.M., Szeliski, R.: Towards internet-scale multi-view stereo. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1434–1441 (2010)
[12]
Furukawa Y and Ponce J Accurate camera calibration from multi-view stereo and bundle adjustment Int. J. Comput. Vis. 2009 84 3 257-268
[13]
Garland, M., Heckbert, P.S.: Surface simplification using quadric error metrics. In: ACM SIGGRAPH, pp. 209–216 (1997)
[14]
Hofer M, Maurer M, and Bischof H Efficient 3D scene abstraction using line segments Comput. Vis. Image Underst. 2017 157 4 167-178
[15]
Kelly T, Femiani J, Wonka P, and Mitra NJ BigSUR: large-scale structured urban reconstruction ACM Trans. Graph. 2017 36 6 204:1-204:16
[16]
Kelly T and Wonka P Interactive architectural modeling with procedural extrusions ACM Trans. Graph. 2011 30 2 14:1-14:15
[17]
Lafarge, F., Mallet, C.: Building large urban environments from unstructured point data. In: IEEE International Conference on Computer Vision (ICCV), pp. 1068–1075 (2011)
[18]
Li M, Nan L, Smith N, and Wonka P Reconstructing building mass models from UAV images Comput. Graph. 2016 54 84-93
[19]
Li M, Wonka P, and Nan L Leibe B, Matas J, Sebe N, and Welling M Manhattan-world urban reconstruction from point clouds Computer Vision – ECCV 2016 2016 Cham Springer 54-69
[20]
Li, Y., Wu, X., Chrysathou, Y., Sharf, A., Cohen-Or, D., Mitra, N.J.: GlobFit: consistently fitting primitives by discovering global relations. In: ACM SIGGRAPH, pp. 52:1–52:12 (2011)
[21]
Liu, J., Wang, J., Fang, T., Tai, C.L., Quan, L.: Higher-order CRF structural segmentation of 3D reconstructed surfaces. In: IEEE International Conference on Computer Vision (ICCV), pp. 2093–2101 (2015)
[22]
Liu, Y., Piramanayagam, S., Monteiro, S.T., Saber, E.: Dense semantic labeling of very-high-resolution aerial imagery and LiDAR with fully-convolutional neural networks and higher-order CRFs. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1561–1570 (2017)
[23]
Musialski P, Wonka P, Aliaga DG, Wimmer M, Gool LV, and Purgathofer W A survey of urban reconstruction Comput. Graph. Forum 2013 32 6 146-177
[24]
Nan, L., Wonka, P.: PolyFit: polygonal surface reconstruction from point clouds. In: IEEE International Conference on Computer Vision (ICCV), pp. 2372–2380 (2017)
[25]
Nguatem, W., Mayer, H.: Modeling urban scenes from pointclouds. In: IEEE International Conference on Computer Vision (ICCV), pp. 3857–3866 (2017)
[26]
Pix4D: Pix4D. https://pix4d.com/
[27]
Poullis C A framework for automatic modeling from point cloud data IEEE Trans. Pattern Anal. Mach. Intell. 2013 35 11 2563-2575
[28]
Rouhani M, Lafarge F, and Alliez P Semantic segmentation of 3D textured meshes for urban scene analysis ISPRS J. Photogramm. Remote. Sens. 2017 123 124-139
[29]
Salinas D, Lafarge F, and Alliez P Structure-aware mesh decimation Comput. Graph. Forum 2015 34 6 211-227
[30]
Schnabel R, Wahl R, and Klein R Efficient RANSAC for point-cloud shape detection Comput. Graph. Forum 2007 26 2 214-226
[31]
Verdie Y, Lafarge F, and Alliez P LOD generation for urban scenes ACM Trans. Graph. 2015 34 3 30:1-30:14
[32]
Volpi M and Tuia D Dense semantic labeling of subdecimeter resolution images with convolutional neural networks IEEE Trans. Geosci. Remote. Sens. 2017 55 2 881-893
[33]
Von Gioi RG, Jakubowicz J, Morel JM, and Randall G LSD: A fast line segment detector with a false detection control IEEE Trans. Pattern Anal. Mach. Intell. 2010 32 4 722-732
[34]
Yang, L., Wu, X., Praun, E., Ma, X.: Tree detection from aerial imagery. In: ACM GIS, pp. 131–137 (2009)
[35]
Zhou Q-Y and Neumann U Daniilidis K, Maragos P, and Paragios N 2.5D dual contouring: a robust approach to creating building models from aerial LiDAR point clouds Computer Vision – ECCV 2010 2010 Heidelberg Springer 115-128
[36]
Zhu, L., Shen, S., Hu, L., Hu, Z.: Variational building modeling from urban MVS meshes. In: IEEE International Conference on 3D Vision (3DV), pp. 318–326 (2017)
Index Terms
- Large Scale Urban Scene Modeling from MVS Meshes
Index terms have been assigned to the content through auto-classification.
Recommendations
LOD Generation for Urban Scenes
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, ...
Urban Scene LOD Vectorized Modeling From Photogrammetry Meshes
Urban scene modeling is a challenging task for the photogrammetry and computer vision community due to its large scale, structural complexity, and topological delicacy. This paper presents an efficient multistep modeling framework for large-scale urban ...
Image-based street-side city modeling
SIGGRAPH Asia '09: ACM SIGGRAPH Asia 2009 papersWe propose an automatic approach to generate street-side 3D photo-realistic models from images captured along the streets at ground level. We first develop a multi-view semantic segmentation method that recognizes and segments each image at pixel level ...
Comments
Information & Contributors
Information
Published In
Sep 2018
842 pages
ISBN:978-3-030-01251-9
DOI:10.1007/978-3-030-01252-6
© Springer Nature Switzerland AG 2018.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 08 September 2018
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 14 Aug 2024
Other Metrics
Citations
View Options
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.
Sign in