Skip to main content
SpringerLink
Log in

ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13662))

Included in the following conference series:

Abstract

Sketch-and-extrude is a common and intuitive modeling process in computer aided design. This paper studies the problem of learning the shape given in the form of point clouds by “inverse” sketch-and-extrude. We present ExtrudeNet, an unsupervised end-to-end network for discovering sketch and extrude from point clouds. Behind ExtrudeNet are two new technical components: 1) an effective representation for sketch and extrude, which can model extrusion with freeform sketches and conventional cylinder and box primitives as well; and 2) a numerical method for computing the signed distance field which is used in the network learning. This is the first attempt that uses machine learning to reverse engineer the sketch-and-extrude modeling process of a shape in an unsupervised fashion. ExtrudeNet not only outputs a compact, editable and interpretable representation of the shape that can be seamlessly integrated into modern CAD software, but also aligns with the standard CAD modeling process facilitating various editing applications, which distinguishes our work from existing shape parsing research. Code is released at https://github.com/kimren227/ExtrudeNet.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Shapr3D: The world’s most intuitive 3d design app. https://www.shapr3d.com/

  2. SOLIDWORKS: 3D CAD design software. https://www.solidworks.com/

  3. Fusion 360: Cloud powered 3d CAD/CAM software for product design, June 2021. https://www.autodesk.com.sg/products/fusion-360/overview

  4. Color and black-and-white noto emoji fonts, and tools for working with them, March 2022. https://github.com/googlefonts/noto-emoji

  5. Batty, C.: SDFGen (2015). https://github.com/christopherbatty/SDFGen

  6. Bridson, R.: Fast poisson disk sampling in arbitrary dimensions. SIGGRAPH Sketches 10, 1 (2007)

    Google Scholar 

  7. Chang, A.X., et al.: ShapeNet: an information-rich 3d model repository. arXiv preprint arXiv:1512.03012 (2015)

  8. Chen, Z., Tagliasacchi, A., Zhang, H.: BSP-Net: generating compact meshes via binary space partitioning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 45–54 (2020)

    Google Scholar 

  9. Deng, B., Genova, K., Yazdani, S., Bouaziz, S., Hinton, G., Tagliasacchi, A.: CVXNet: learnable convex decomposition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 31–44 (2020)

    Google Scholar 

  10. Farin, G.: Curves and Surfaces for CAGD: A Practical Guide, 5th edn. Morgan Kaufmann Publishers Inc., San Francisco (2001)

    Google Scholar 

  11. Ganin, Y., Bartunov, S., Li, Y., Keller, E., Saliceti, S.: Computer-aided design as language. arXiv preprint arXiv:2105.02769 (2021)

  12. Hao, Z., Averbuch-Elor, H., Snavely, N., Belongie, S.: DualSDF: semantic shape manipulation using a two-level representation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7631–7641 (2020)

    Google Scholar 

  13. Kania, K., Zieba, M., Kajdanowicz, T.: UCSG-Net-unsupervised discovering of constructive solid geometry tree. arXiv preprint arXiv:2006.09102 (2020)

  14. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

  15. Kintel, M., Wolf, C.: OpenSCAD. GNU General Public License, p GNU General Public License (2014)

    Google Scholar 

  16. Laidlaw, D.H., Trumbore, W.B., Hughes, J.F.: Constructive solid geometry for polyhedral objects. In: Proceedings of the 13th Annual Conference on Computer Graphics and Interactive Techniques, pp. 161–170 (1986)

    Google Scholar 

  17. Lorensen, W.E., Cline, H.E.: Marching cubes: a high resolution 3d surface construction algorithm. ACM SIGGRAPH Comput. Graph. 21(4), 163–169 (1987)

    Article  Google Scholar 

  18. Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.: Occupancy networks: learning 3d reconstruction in function space. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4460–4470 (2019)

    Google Scholar 

  19. Para, W.R., et al.: SketchGen: generating constrained cad sketches. arXiv preprint arXiv:2106.02711 (2021)

  20. Park, J.J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: DeepSDF: learning continuous signed distance functions for shape representation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 165–174 (2019)

    Google Scholar 

  21. Paschalidou, D., Ulusoy, A.O., Geiger, A.: Superquadrics revisited: learning 3d shape parsing beyond cuboids. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10344–10353 (2019)

    Google Scholar 

  22. Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’ Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp. 8024–8035. Curran Associates, Inc. (2019). http://papers.neurips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf

  23. Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652–660 (2017)

    Google Scholar 

  24. Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems, vol. 30 (2017)

    Google Scholar 

  25. Ren, D., et al.: CSG-stump: a learning friendly CSG-like representation for interpretable shape parsing. arXiv preprint arXiv:2108.11305 (2021)

  26. Requicha, A.A., Voelcker, H.B.: Constructive solid geometry (1977)

    Google Scholar 

  27. Roscoe, L., et al.: Stereolithography interface specification. America-3D Systems Inc 27(2020), 10 (1988)

    Google Scholar 

  28. Sanchez-Reyes, J.: Single-valued curves in polar coordinates. Comput. Aided Des. 22(1), 19–26 (1990)

    Article  MATH  Google Scholar 

  29. Sánchez-Reyes, J.: Single-valued spline curves in polar coordinates. Comput. Aided Des. 24(6), 307–315 (1992)

    Article  MATH  Google Scholar 

  30. Sederberg, T.W., Anderson, D.C., Goldman, R.N.: Implicit representation of parametric curves and surfaces. Comput. Vis. Graph. Image Process. 28(1), 72–84 (1984)

    Article  MATH  Google Scholar 

  31. Sederberg, T.W., Zheng, J., Klimaszewski, K., Dokken, T.: Approximate implicitization using monoid curves and surfaces. Graph. Model. Image Process. 61(4), 177–198 (1999). https://doi.org/10.1006/gmip.1999.0497

    Article  Google Scholar 

  32. Sharma, G., Goyal, R., Liu, D., Kalogerakis, E., Maji, S.: CSGNet: neural shape parser for constructive solid geometry. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5515–5523 (2018)

    Google Scholar 

  33. 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, pp. 2635–2643 (2017)

    Google Scholar 

  34. 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. (ToG) 38(5), 1–12 (2019)

    Article  Google Scholar 

  35. Wu, R., Xiao, C., Zheng, C.: DeepCAD: a deep generative network for computer-aided design models. arXiv preprint arXiv:2105.09492 (2021)

  36. Yu, F., et al.: CAPRI-Net: learning compact CAD shapes with adaptive primitive assembly. arXiv preprint arXiv:2104.05652 (2021)

  37. Zheng, J., Sederberg, T.W.: A direct approach to computing the \({\mu }\)-basis of planar rational curves. J. Symb. Comput. 31(5), 619–629 (2001). https://doi.org/10.1006/jsco.2001.0437

Download references

Acknowledgements

The work is partially supported by a joint WASP/NTU project (04INS000440C130), Monash FIT Startup Grant, and SenseTime Gift Fund.

Author information

Authors and Affiliations

  1. Nanyang Technological University, Singapore, Singapore

    Daxuan Ren, Jianmin Zheng, Jianfei Cai, Jiatong Li & Junzhe Zhang

  2. Sensetime Research, Singapore, Singapore

    Daxuan Ren, Jiatong Li & Junzhe Zhang

  3. Monash University, Melbourne, Australia

    Jianfei Cai

Authors
  1. Daxuan Ren
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jianmin Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jianfei Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jiatong Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Junzhe Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jianmin Zheng .

Editor information

Editors and Affiliations

  1. Tel Aviv University, Tel Aviv, Israel

    Shai Avidan

  2. University College London, London, UK

    Gabriel Brostow

  3. Google AI, Accra, Ghana

    Moustapha Cissé

  4. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Facebook (United States), Menlo Park, CA, USA

    Tal Hassner

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 13357 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Ren, D., Zheng, J., Cai, J., Li, J., Zhang, J. (2022). ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13662. Springer, Cham. https://doi.org/10.1007/978-3-031-20086-1_28

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20086-1_28

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20085-4

  • Online ISBN: 978-3-031-20086-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation