method such as (Fayolle and Pasko, 2016; Wu et al.,
2018; Du et al., 2018).
Missing Details. In some rare cases, ﬁne geometric
details are not reconstructed correctly with the pro-
posed approach. This can be mitigated by increasing
the point cloud density as well as the GA’s maximum
number of iterations. In addition, the objective func-
tion weights (Equation 1) can be tweaked for a spe-
ciﬁc data set. A reduction of parameter sensitivity is
planned for future work.
Unconnected Cylinders. Since the height of a cylin-
der is estimated using the associated point cloud, it
can happen that the cylinder is not connected to other
parts and small gaps appear between primitives. This
can be mitigated by adding cylinders to the GA to ﬁnd
their optimal capping planes.
6 CONCLUSION
In this paper, a hybrid primitive segmentation and ﬁt-
ting pipeline is proposed. Our approach is capable of
handling large point clouds in reasonable time. As fu-
ture work, we plan to tackle the limitations discussed
in Section 5.4. In addition, we plan to add extra shape
types, such as arbitrary convex polytopes.
REFERENCES
Attene, M., Falcidieno, B., and Spagnuolo, M. (2006). Hi-
erarchical mesh segmentation based on ﬁtting primi-
tives. The Visual Computer, 22(3):181–193.
Benk
˝
o, P., Martin, R. R., and V
´
arady, T. (2001). Algorithms
for reverse engineering boundary representation mod-
els. Computer-Aided Design, 33(11):839–851.
Breunig, M. M., Kriegel, H.-P., Ng, R. T., and Sander, J.
(2000). Lof: Identifying density-based local outliers.
SIGMOD Rec., 29(2):93–104.
Cohen-Steiner, D., Alliez, P., and Desbrun, M. (2004). Vari-
ational shape approximation. ACM Trans. Graphics,
3(23):905–914.
Czerniawski, T., Sankaran, B., Nahangi, M., Haas, C., and
Leite, F. (2018). 6D DBSCAN-based segmentation of
building point clouds for planar object classiﬁcation.
Automation in Construction, 88(December 2017):44–
58.
Du, T., Inala, J. P., Pu, Y., Spielberg, A., Schulz, A., Rus,
D., Solar-Lezama, A., and Matusik, W. (2018). In-
versecsg: Automatic conversion of 3d models to csg
trees. ACM Trans. Graph., 37(6):213:1–213:16.
Ester, M., Kriegel, H.-P., Sander, J., and Xu, X. (1996).
A density-based algorithm for discovering clusters a
density-based algorithm for discovering clusters in
large spatial databases with noise. In Proceedings of
the Second International Conference on Knowledge
Discovery and Data Mining, KDD’96, pages 226–
231. AAAI Press.
Fayolle, P.-A. and Pasko, A. (2016). An evolutionary ap-
proach to the extraction of object construction trees
from 3d point clouds. Computer-Aided Design, 74:1–
17.
Fischler, M. A. and Bolles, R. C. (1981). Random sample
consensus: a paradigm for model ﬁtting with appli-
cations to image analysis and automated cartography.
Communications of the ACM, 24(6):381–395.
Friedrich, M., Cuevas, F. G., Sedlmeier, A., and Ebert, A.
(2019). Evolutionary generation of primitive-based
mesh abstractions. In Proceedings of WSCG 2019.
Fukuda, K. and Prodon, A. (1995). Double description
method revisited. In Combinatorics and Computer
Science.
Genova, K., Cole, F., Vlasic, D., Sarna, A., Freeman, W. T.,
and Funkhouser, T. (2019). Learning shape templates
with structured implicit functions. arXiv preprint
arXiv:1904.06447.
Kaiser, A., Zepeda, J. A. Y., and Boubekeur, T. (2019). A
survey of simple geometric primitives detection meth-
ods for captured 3d data. Computer Graphics Forum,
38(1):167–196.
Kalogerakis, E., Hertzmann, A., and Singh, K. (2010).
Learning 3d mesh segmentation and labeling. ACM
Trans. Graph., 29(4):102:1–102:12.
Kim, V. G., Li, W., Mitra, N. J., Chaudhuri, S., DiVerdi,
S., and Funkhouser, T. (2013). Learning part-based
templates from large collections of 3d shapes. ACM
Trans. Graph., 32(4):70:1–70:12.
Lavou
´
e, G., Dupont, F., and Baskurt, A. (2005). A new
CAD mesh segmentation method, based on curvature
tensor analysis. Computer-Aided Design, 37(10):975–
987.
Le, T. and Duan, Y. (2017). A primitive-based 3d segmenta-
tion algorithm for mechanical cad models. Computer
Aided Geometric Design, 52:231–246.
Li, L., Sung, M., Dubrovina, A., Yi, L., and Guibas, L. J.
(2019). Supervised ﬁtting of geometric primitives to
3d point clouds. In Proceedings of the IEEE Con-
ference on Computer Vision and Pattern Recognition,
pages 2652–2660.
Li, M., Wonka, P., and Nan, L. (2016). Manhattan-world
urban reconstruction from point clouds. In ECCV.
Li, Y., Wu, X., Chrysathou, Y., Sharf, A., Cohen-Or, D.,
and Mitra, N. J. (2011). Globﬁt: Consistently ﬁtting
primitives by discovering global relations. ACM trans-
actions on graphics (TOG), 30(4):52.
Marshall, D., Lukacs, G., and Martin, R. (2001). Ro-
bust segmentation of primitives from range data in
the presence of geometric degeneracy. IEEE Trans-
actions on Pattern Analysis and Machine Intelligence,
23(3):304–314.
Monszpart, A., Mellado, N., Brostow, G. J., and Mitra, N. J.
(2015). RAPter: Rebuilding man-made scenes with
regular arrangements of planes. ACM Trans. Graph.,
34(4):103:1–103:12.
Nan, L. and Wonka, P. (2017). Polyﬁt: Polygonal surface
reconstruction from point clouds. In Proceedings of