Skip to main content
SpringerLink
Log in

ShapeCreator: 3D Shape Generation from Isomorphic Datasets Based on Autoencoder

  • Conference paper
  • First Online:
MultiMedia Modeling (MMM 2018)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 10705))

Included in the following conference series:

  • 2766 Accesses

Abstract

With the development of 3D digital geometry media, the creation of 3D content is becoming more and more important. This paper presents a novel method for 3D shape generation from the isomorphic examples in terms of Autoencoder. A structure-aware shape representation is firstly built from the given examples with same category. The representation describes the shapes in a unified manner no matter how the shape structure varies. Then, an Autoencoder model is introduced to establish a bidirectional mapping between the high-dimensional representing space and a 2D latent space. This bridges the existed examples and the latent generated shapes. In the one hand, the sample data in representation space is transferred to a lower dimension by the encoder of Autoencoder to form a latent space. Then the latent space is checked and visualized to guarantee created shapes meaningful. In the other hand, decoder of Autoencoder is able to transform new data from the latent space to isomorphic representation, and novel structures are constructed from the decoded representation. This scheme facilitate the operation of 3D creation a lot. Experimental results prove the effectiveness of the proposed approach.

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 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
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. Kalogerakis, E., Hertzmann, A., Singh, K.: Learning 3D mesh segmentation and labeling. ACM Trans. Graph. (TOG) 29(4), 102 (2010). ACM

    Article  Google Scholar 

  2. Huang, Q., Koltun, V., Guibas, L.: Joint shape segmentation with linear programming. ACM Trans. Graph. (TOG) 30(6), 125 (2011). ACM

    Google Scholar 

  3. Sidi, O., et al.: Unsupervised co-segmentation of a set of shapes via descriptor-space spectral clustering. 30(6), 126 (2011). ACM

    Google Scholar 

  4. Kim, V.G., Li, W., Mitra, N.J., DiVerdi, S., Funkhouser, T.: Learning part-based templates from large collections of 3D shapes. ACM Trans. Graph. (TOG) 32, 70 (2013)

    MATH  Google Scholar 

  5. Mitra, N., Wand, M., Zhang, H.R., Cohen-Or, D., Kim, V., Huang, Q.X.: Structure-aware shape processing. In: SIGGRAPH Asia 2013 Courses, p. 1. ACM (2013)

    Google Scholar 

  6. Laga, H., Mortara, M.: Geometry and context for semantic correspondences and functionality recognition in man-made 3D shapes. ACM Trans. Graph. (TOG) 32, 150 (2013)

    Article  Google Scholar 

  7. Hu, R., van Kaick, O., Wu, B., Huang, H., Shamir, A., Zhang, H.: Learning how objects function via co-analysis of interactions. ACM Trans. Graph. (TOG) 35, 47 (2016)

    Article  Google Scholar 

  8. Kim, V.G., Chaudhuri, S., Guibas, L., Funkhouser, T.: Shape2pose: human-centric shape analysis. ACM Trans. Graph. (TOG) 33(4), 120 (2014)

    Google Scholar 

  9. Chaudhuri, S., Kalogerakis, E., Guibas, L., Koltun, V.: Probabilistic reasoning for assembly-based 3D modeling. ACM Trans. Graph. TOG 30, 35 (2011)

    Google Scholar 

  10. Kalogerakis, E., Chaudhuri, S., Koller, D., Koltun, V.: A probabilistic model for component-based shape synthesis. ACM Trans. Graph. (TOG) 31(4), 55 (2012)

    Article  Google Scholar 

  11. Fish, N., Averkiou, M., Kaick, Van, Cohen-Or, D., Mitra, N.J.: Meta-representation of shape families. ACM Trans. Graph. (TOG) 33(4), 34 (2014)

    Article  Google Scholar 

  12. Hilaga, M., et al.: Topology matching for fully automatic similarity estimation of 3D shapes. In: Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques. ACM (2001)

    Google Scholar 

  13. Barra, V., Biasotti, S.: 3D shape retrieval using kernels on extended Reeb graphs. Pattern Recogn. 46(11), 2985–2999 (2013)

    Article  MATH  Google Scholar 

  14. Liu, H., Vimont, U., Wand, M., Cani, M.P., Mitra, N.J.: Replaceable substructures for efficient part-based modeling. Comput. Graph. Forum 34, 503–513 (2015)

    Article  Google Scholar 

  15. Huang, S.S., Fu, H., Wei, L.Y., Hu, S.M.: Support substructures: support-induced part-level structural representation. IEEE Trans. Vis. Comput. Graph. 22(8), 2024–2036 (2016)

    Article  Google Scholar 

  16. Alhashim, I., Li, H., Xu, K., Cao, J., Ma, R., Zhang, H.: Topology-varying 3D shape creation via structural blending. ACM Trans. Graph. (TOG) 33(4), 158 (2014)

    Article  Google Scholar 

  17. Kreavoy, V., Julius, D., Sheffer, A.: Model composition from interchangeable components. In: Computer Graphics and Applications, pp. 129–138 (2007)

    Google Scholar 

  18. Xu, K., Zhang, H., Cohen-Or, D., Chen, B.: Fit and diverse: set evolution for inspiring 3D shape galleries. ACM Trans. Graph. (TOG) 31(4), 57 (2012)

    Article  MathSciNet  Google Scholar 

  19. Zheng, Y., Cohen-Or, D., Mitra, N.J.: Smart variations: functional substructures for part compatibility. Comput. Graph. Forum 32(2pt2), 195–204 (2013)

    Article  Google Scholar 

  20. Huang, H., Kalogerakis, E., Marlin, B.: Analysis and synthesis of 3D shape families via deep-learned generative models of surfaces. Comput. Graph. Forum 34, 25–38 (2015)

    Article  Google Scholar 

  21. Li, J., Xu, K., Chaudhuri, S., Yumer, E., Zhang, H., Guibas, L.: GRASS: Generative Recursive Autoencoders for Shape Structures (2017). arXiv preprint arXiv:1705.02090

  22. Alhashim, I., Xu, K., Zhuang, Y., Cao, J., Simari, P., Zhang, H.: Deformation-driven topology-varying 3D shape correspondence. ACM Trans. Graph. TOG 34, 236 (2015)

    Google Scholar 

  23. Williams, D.R.G.H.R., Hinton, G.: Learning representations by back-propagating errors. Nature 323(6088), 533–538 (1986)

    Article  MATH  Google Scholar 

  24. Chen, D.Y., Tian, X.P., Shen, Y.T., Ouhyoung, M.: On visual similarity based 3D model retrieval. Comput. Graph. Forum 22(3), 223–232 (2003)

    Article  Google Scholar 

  25. Chang, A.X., et al.: Shapenet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)

Download references

Acknowledgement

This work was supported by National High Technology Research and Development Program of China (No. 2007AA01Z334), National Natural Science Foundation of China (Nos. 61321491 and 61272219), Innovation Fund of State Key Laboratory for Novel Software Technology (Nos. ZZKT2013A12 and ZZKT2016A11), and Program for New Century Excellent Talents in University of China (NCET-04-04605).

Author information

Authors and Affiliations

  1. State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China

    Yunjie Wu, Zhengxing Sun, Youcheng Song & Hongyan Li

Authors
  1. Yunjie Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhengxing Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Youcheng Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hongyan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhengxing Sun .

Editor information

Editors and Affiliations

  1. Alpen-Adria-Universität Klagenfurt, Klagenfurt, Austria

    Klaus Schoeffmann

  2. Chulalongkorn University, Bangkok, Thailand

    Thanarat H. Chalidabhongse

  3. City University of Hong Kong, Hong Kong, China

    Chong Wah Ngo

  4. Chulalongkorn University, Bangkok, Thailand

    Supavadee Aramvith

  5. Dublin City University, Dublin, Ireland

    Noel E. O’Connor

  6. Gwangju Institute of Science and Technology, Gwangju, Korea (Republic of)

    Yo-Sung Ho

  7. Tampere University of Technology, Tampere, Finland

    Moncef Gabbouj

  8. Rutgers University, Piscataway, New Jersey, USA

    Ahmed Elgammal

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer International Publishing AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Wu, Y., Sun, Z., Song, Y., Li, H. (2018). ShapeCreator: 3D Shape Generation from Isomorphic Datasets Based on Autoencoder. In: Schoeffmann, K., et al. MultiMedia Modeling. MMM 2018. Lecture Notes in Computer Science(), vol 10705. Springer, Cham. https://doi.org/10.1007/978-3-319-73600-6_23

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-73600-6_23

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-73599-3

  • Online ISBN: 978-3-319-73600-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation