Skip to main content
Springer Nature Link
Log in

Unsupervised Description of 3D Shapes by Superquadrics Using Deep Learning

  • Conference paper
  • First Online:
Computer Vision and Machine Intelligence

Part of the book series: Lecture Notes in Networks and Systems ((LNNS,volume 586))

  • 929 Accesses

Abstract

The decomposition of 3D shapes into simple yet representative components is a very intriguing topic in computer vision as it is very useful for many possible applications. Superquadrics may be used with benefit to obtain an implicit representation of the 3D shapes, as they allow to represent a wide range of possible forms by few parameters. However, in the computation of the shape representation, there is often an intricate trade-off between the variation of the represented geometric forms and the accuracy in such implicit approaches. In this paper, we propose an improved loss function, and we introduce beneficial computational techniques. By comparing results obtained by our new technique to the baseline method, we demonstrate that our results are more reliable and accurate, as well as much faster to obtain.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Barr, A.H.: Superquadrics and angle-preserving transformations. IEEE Comput. Graph. Appl. 1(1), 11–23 (1981)

    Article  Google Scholar 

  2. Biederman, I.: Human image understanding: Recent research and a theory. Comput. Vis. Graph. Image Process. 32(1), 29–73 (1985)

    Article  Google Scholar 

  3. Binford, I.: Visual perception by computer. In: IEEE Conference of Systems and Control (1971)

    Google Scholar 

  4. Brock, A., Lim, T., Ritchie, J.M., Weston, N.: Generative and discriminative voxel modeling with convolutional neural networks. arXiv preprint arXiv:1608.04236 (2016)

  5. Chang, A.X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., et al.: Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012 (2015)

  6. Chevalier, L., Jaillet, F., Baskurt, A.: Segmentation and superquadric modeling of 3d objects (2003)

    Google Scholar 

  7. 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 

  8. Fey, M., Lenssen, J.E., Weichert, F., Müller, H.: Splinecnn: Fast geometric deep learning with continuous b-spline kernels. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 869–877 (2018)

    Google Scholar 

  9. He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision. pp. 1026–1034 (2015)

    Google Scholar 

  10. Huang, J., Gao, J., Ganapathi-Subramanian, V., Su, H., Liu, Y., Tang, C., Guibas, L.J.: Deepprimitive: Image decomposition by layered primitive detection. Comput. Vis. Media 4(4), 385–397 (2018)

    Article  Google Scholar 

  11. Kawana, Y., Mukuta, Y., Harada, T.: Neural star domain as primitive representation. arXiv preprint arXiv:2010.11248 (2020)

  12. Li, C., Zeeshan Zia, M., Tran, Q.H., Yu, X., Hager, G.D., Chandraker, M.: Deep supervision with shape concepts for occlusion-aware 3d object parsing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 5465–5474 (2017)

    Google Scholar 

  13. Maron, H., Galun, M., Aigerman, N., Trope, M., Dym, N., Yumer, E., Kim, V.G., Lipman, Y.: Convolutional neural networks on surfaces via seamless toric covers. ACM Trans. Graph. 36(4), 71–1 (2017)

    Article  Google Scholar 

  14. Maturana, D., Scherer, S.: Voxnet: A 3d convolutional neural network for real-time object recognition. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 922–928. IEEE (2015)

    Google Scholar 

  15. Monti, F., Boscaini, D., Masci, J., Rodola, E., Svoboda, J., Bronstein, M.M.: Geometric deep learning on graphs and manifolds using mixture model cnns. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 5115–5124 (2017)

    Google Scholar 

  16. 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. pp. 1060–1070 (2020)

    Google Scholar 

  17. Paschalidou, D., Katharopoulos, A., Geiger, A., Fidler, S.: Neural parts: Learning expressive 3d shape abstractions with invertible neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 3204–3215 (2021)

    Google Scholar 

  18. 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 

  19. Pentland, A.: Parts: Structured descriptions of shape. In: AAAI. pp. 695–701 (1986)

    Google Scholar 

  20. Pilu, M., Fisher, R.B.: Equal-distance sampling of superellipse models (1995)

    Google Scholar 

  21. 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 

  22. Roberts, L.G.: Machine perception of three-dimensional solids. Ph.D. thesis, Massachusetts Institute of Technology (1963)

    Google Scholar 

  23. Shi, W., Rajkumar, R.: Point-gnn: Graph neural network for 3d object detection in a point cloud. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 1711–1719 (2020)

    Google Scholar 

  24. Sinha, A., Bai, J., Ramani, K.: Deep learning 3d shape surfaces using geometry images. In: European Conference on Computer Vision. pp. 223–240. Springer (2016)

    Google Scholar 

  25. Smith, L.N.: Cyclical learning rates for training neural networks. In: 2017 IEEE winter conference on applications of computer vision (WACV). pp. 464–472. IEEE (2017)

    Google Scholar 

  26. Solina, F., Bajcsy, R.: Recovery of parametric models from range images: The case for superquadrics with global deformations. IEEE Trans. Pattern Anal. Mach. Intell. 12(2), 131–147 (1990)

    Article  Google Scholar 

  27. 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 

  28. Verma, N., Boyer, E., Verbeek, J.: Feastnet: Feature-steered graph convolutions for 3d shape analysis. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 2598–2606 (2018)

    Google Scholar 

  29. Wu, B., Liu, Y., Lang, B., Huang, L.: Dgcnn: Disordered graph convolutional neural network based on the gaussian mixture model. Neurocomputing 321, 346–356 (2018)

    Article  Google Scholar 

  30. Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., Xiao, J.: 3d shapenets: A deep representation for volumetric shapes. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 1912–1920 (2015)

    Google Scholar 

  31. Zou, C., Yumer, E., Yang, J., Ceylan, D., Hoiem, D.: 3d-prnn: generating shape primitives with recurrent neural networks. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 900–909 (2017)

    Google Scholar 

Download references

Acknowledgements

The current work was supported by the European Regional Development Fund, EFRE 85037495. Furthermore, the authors acknowledge the support by BTU Graduate Research School (STIBET short-term scholarship for international PhD Students sponsored by the German Academic Exchange Service (DAAD) with funds of the German Federal Foreign Office).

Author information

Authors and Affiliations

  1. Brandenburg University of Technology, Cottbus, Germany

    Mahmoud Eltaher & Michael Breuß

  2. Al-Azhar University, Cairo, Egypt

    Mahmoud Eltaher

Authors
  1. Mahmoud Eltaher
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Michael Breuß
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mahmoud Eltaher .

Editor information

Editors and Affiliations

  1. Computer Vision Laboratory, University of Sassari, Alghero, Sassari, Italy

    Massimo Tistarelli

  2. Computer Vision and Biometrics Lab, Department of Information Technology, Indian Institute of Information Technology Allahabad, Prayagraj, India

    Shiv Ram Dubey

  3. Computer Vision and Biometrics Lab, Department of Information Technology, Indian Institute of Information Technology, Allahabad, India

    Satish Kumar Singh

  4. University of Münster, Münster, Germany

    Xiaoyi Jiang

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Eltaher, M., Breuß, M. (2023). Unsupervised Description of 3D Shapes by Superquadrics Using Deep Learning. In: Tistarelli, M., Dubey, S.R., Singh, S.K., Jiang, X. (eds) Computer Vision and Machine Intelligence. Lecture Notes in Networks and Systems, vol 586. Springer, Singapore. https://doi.org/10.1007/978-981-19-7867-8_9

Download citation

Publish with us

Policies and ethics