Advertisement

ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12352)

Abstract

We propose a novel, end-to-end trainable, deep network called ParSeNet that decomposes a 3D point cloud into parametric surface patches, including B-spline patches as well as basic geometric primitives. ParSeNet is trained on a large-scale dataset of man-made 3D shapes and captures high-level semantic priors for shape decomposition. It handles a much richer class of primitives than prior work, and allows us to represent surfaces with higher fidelity. It also produces repeatable and robust parametrizations of a surface compared to purely geometric approaches. We present extensive experiments to validate our approach against analytical and learning-based alternatives. Our source code is publicly available at: https://hippogriff.github.io/parsenet.

Notes

Acknowledgements

This research is funded in part by NSF (#1617333, #1749833) and Adobe. Our experiments were performed in the UMass GPU cluster funded by the MassTech Collaborative. We thank Matheus Gadelha for helpful discussions.

Supplementary material

504444_1_En_16_MOESM1_ESM.pdf (1.9 mb)
Supplementary material 1 (pdf 1935 KB)

References

  1. 1.
    Ahmed, E.: Deep learning advances on different 3D data representations: a survey. Computing Research Repository (CoRR) abs/1808.01462 (2019)Google Scholar
  2. 2.
    Eck, M., Hoppe, H.: Automatic reconstruction of B-spline surfaces of arbitrary topological type. In: SIGGRAPH (1996)Google Scholar
  3. 3.
    Farin, G.: Curves and Surfaces for CAGD, 5th edn. Morgan Kaufmann, San Francisco (2002)Google Scholar
  4. 4.
    Foley, J.D., van Dam, A., Feiner, S.K., Hughes, J.F.: Computer Graphics: Principles and Practice, 2nd edn. Addison-Wesley Longman Publishing Co. Inc., Boston (1990)zbMATHGoogle Scholar
  5. 5.
    Gao, J., Tang, C., Ganapathi-Subramanian, V., Huang, J., Su, H., Guibas, L.J.: DeepSpline: data-driven reconstruction of parametric curves and surfaces. Computing Research Repository (CoRR) abs/1901.03781 (2019)Google Scholar
  6. 6.
    Hoppe, H., et al.: Piecewise smooth surface reconstruction. In: Proceedings of SIGGRAPH (1994)Google Scholar
  7. 7.
    Kaiser, A., Ybanez Zepeda, J.A., Boubekeur, T.: A survey of simple geometric primitives detection methods for captured 3D data. Comput. Graph. Forum 38(1), 167–196 (2019)CrossRefGoogle Scholar
  8. 8.
    Koch, S., et al.: ABC: a big cad model dataset for geometric deep learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019Google Scholar
  9. 9.
    Kong, S., Fowlkes, C.: Recurrent pixel embedding for instance grouping. In: 2018 Conference on Computer Vision and Pattern Recognition (CVPR) (2018)Google Scholar
  10. 10.
    Krishnamurthy, V., Levoy, M.: Fitting smooth surfaces to dense polygon meshes. In: SIGGRAPH (1996)Google Scholar
  11. 11.
    Li, L., Sung, M., Dubrovina, A., Yi, L., Guibas, L.J.: Supervised fitting of geometric primitives to 3D point clouds. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019Google Scholar
  12. 12.
    Paschalidou, D., Ulusoy, A.O., Geiger, A.: Superquadrics revisited: Learning 3D shape parsing beyond cuboids. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10336–10345 (2019)Google Scholar
  13. 13.
    Paschalidou, D., Gool, L.V., Geiger, A.: Learning unsupervised hierarchical part decomposition of 3d objects from a single RGB image. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020Google Scholar
  14. 14.
    Piegl, L., Tiller, W.: The NURBS Book. Monographs in Visual Communication, 2nd edn. Springer, Heidelberg (1997).  https://doi.org/10.1007/978-3-642-59223-2CrossRefzbMATHGoogle Scholar
  15. 15.
    Schnabel, R., Wahl, R., Klein, R.: Efficient RANSAC for point-cloud shape detection. Comput. Graph. Forum 26, 214–226 (2007)CrossRefGoogle Scholar
  16. 16.
    Schneider, P.J., Eberly, D.: Geometric Tools for Computer Graphics. Elsevier Science Inc., Amsterdam (2002)Google Scholar
  17. 17.
    Sharma, G., Goyal, R., Liu, D., Kalogerakis, E., Maji, S.: CSGNet: neural shape parser for constructive solid geometry. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5515–5523 (2018)Google Scholar
  18. 18.
    Sharma, G., Goyal, R., Liu, D., Kalogerakis, E., Maji, S.: Neural shape parsers for constructive solid geometry. Computing Research Repository (CoRR) abs/1912.11393 (2019). http://arxiv.org/abs/1912.11393
  19. 19.
    Silverman, B.W.: Density Estimation for Statistics and Data Analysis. Chapman & Hall, London (1986)CrossRefGoogle Scholar
  20. 20.
    Smirnov, D., Fisher, M., Kim, V.G., Zhang, R., Solomon, J.: Deep parametric shape predictions using distance fields. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020Google Scholar
  21. 21.
    Sorkine, O., Alexa, M.: As-rigid-as-possible surface modeling. In: Symposium on Geometry Processing, pp. 109–116 (2007)Google Scholar
  22. 22.
    Sun, C., Zou, Q., Tong, X., Liu, Y.: Learning adaptive hierarchical cuboid abstractions of 3D shape collections. ACM Trans. Graph. (SIGGRAPH Asia) 38(6), 1–3 (2019)CrossRefGoogle Scholar
  23. 23.
    Tian, Y., et al.: Learning to infer and execute 3D shape programs. In: International Conference on Learning Representations (2019)Google Scholar
  24. 24.
    Tulsiani, S., Su, H., Guibas, L.J., Efros, A.A., Malik, J.: Learning shape abstractions by assembling volumetric primitives. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017Google Scholar
  25. 25.
    Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph CNN for learning on point clouds. ACM Trans. Graph. 38(5), 1–12 (2019)CrossRefGoogle Scholar
  26. 26.
    Yumer, M.E., Kara, L.B.: Surface creation on unstructured point sets using neural networks. Comput. Aided Des. 44(7), 644–656 (2012)CrossRefGoogle Scholar
  27. 27.
    Zou, C., Yumer, E., Yang, J., Ceylan, D., Hoiem, D.: 3D-PRNN: generating shape primitives with recurrent neural networks. In: The IEEE International Conference on Computer Vision (ICCV) (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.University of Massachusetts AmherstAmherstUSA
  2. 2.Adobe ResearchSan JoseUSA
  3. 3.IIT, BombayBombayIndia

Personalised recommendations