Skip to main content
SpringerLink
Log in
Book cover

Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

PRCV 2019: Pattern Recognition and Computer Vision pp 378–389Cite as

ODCN: Optimized Dilated Convolution Network for 3D Shape Segmentation

  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 11859))

Abstract

3D shape segmentation is a vital and fundamental issue in 3D shape analysis tasks, and the multi-view paradigm is one of practical approaches to solve it. The typical multi-view paradigm contains an image-based convolutional neural network (CNN) for effective view-based semantic segmentation. To improve the accuracy of multi-view paradigm, this paper presents a new dilated convolution network called Optimized Dilated Convolution Network (ODCN). We derive a novel network architecture by using the gradient descent with momentum algorithm to minimize some objective functions related to neural network propagation. In addition, the dilated convolution, which increases the resolution of output feature maps without reducing the receptive field of network, is adopted for semantic segmentation. Experimental results verify that the proposed method achieves better performance over other state-of-the-art methods.

Student as first author.

This is a preview of subscription content, 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

Learn about institutional subscriptions

References

  1. Guo, K., Zou, D., Chen, X.: 3d mesh labeling via deep convolutional neural networks. ACM Trans. Graph. 35(1), 3:1–3:12 (2015)

    Article  Google Scholar 

  2. Kalogerakis, E., Averkiou, M., Maji, S., Chaudhuri, S.: 3D shape segmentation with projective convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3779–3788 (2017)

    Google Scholar 

  3. Wang, P., Gan, Y., Shui, P.: 3D shape segmentation via shape fully convolutional networks. Comput. Graph. 70, 128–139 (2018)

    Article  Google Scholar 

  4. Shu, Z., et al.: Scribble based 3D shape segmentation via weakly-supervised learning. IEEE Trans. Vis. Comput. Graph. 1, 1 (2019)

    Article  Google Scholar 

  5. Wu, Z., Wang, Y., Shou, R., Chen, B., Liu, X.: Unsupervised co-segmentation of 3D shapes via affinity aggregation spectral clustering. Comput. Graph. 37(6), 628–637 (2013)

    Article  Google Scholar 

  6. Sander, P.V., Snyder, J., Gortler, S.J., Hoppe, H.: Texture mapping progressive meshes. In: Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques, pp. 409–416. ACM (2001)

    Google Scholar 

  7. Shalom, S., Shapira, L., Shamir, A., Cohen-Or, D.: Part analogies in sets of objects. In: Proceedings of the 1st Eurographics Conference on 3D Object Retrieval, pp. 33–40 (2008)

    Google Scholar 

  8. Zuckerberger, E., Tal, A., Shlafman, S.: Polyhedral surface decomposition with applications. Comput. Graph. 26(5), 733–743 (2002)

    Article  Google Scholar 

  9. He, C., Wang, C.: A survey on segmentation of 3D models. Wirel. Pers. Commun. 102(4), 3835–3842 (2018)

    Article  MathSciNet  Google Scholar 

  10. Chen, X., Golovinskiy, A., Funkhouser, T.: A benchmark for 3D mesh segmentation. In: ACM Transactions on Graphics, pp. 73:1–73:12. ACM (2009)

    Google Scholar 

  11. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  12. Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)

    Google Scholar 

  13. Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv:1511.07122 (2015)

  14. Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3d shape recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 945–953 (2015)

    Google Scholar 

  15. Le, T., Bui, G., Duan, Y.: A multi-view recurrent neural network for 3D mesh segmentation. Comput. Graph. 66, 103–112 (2017)

    Article  Google Scholar 

  16. Yu, F., Koltun, V., Funkhouser, T.: Dilated residual networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 472–480 (2017)

    Google Scholar 

  17. Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. arXiv:1412.7062 (2014)

  18. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)

  19. Bertsekas, D.P.: Nonlinear programming. J. Oper. Res. Soc. 48(3), 334 (1997)

    Article  Google Scholar 

  20. Qian, N.: On the momentum term in gradient descent learning algorithms. Neural Netw. 12(1), 145–151 (1999)

    Article  MathSciNet  Google Scholar 

  21. Gal, R., Cohen-Or, D.: Salient geometric features for partial shape matching and similarity. ACM Trans. Graph. 25(1), 130–150 (2006)

    Article  Google Scholar 

  22. Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Trans. Pattern Anal. Mach. Intell. 4, 509–522 (2002)

    Article  Google Scholar 

  23. Polyak, B.: Some methods of speeding up the convergence of iteration methods. USSR Comput. Math. Math. Phys. 4(5), 1–17 (1964)

    Article  Google Scholar 

  24. Kalogerakis, E., Hertzmann, A., Singh, K.: Learning 3D mesh segmentation and labeling. ACM Trans. Graph. 29(4), 102 (2010)

    Article  Google Scholar 

  25. Wang, Y., Gong, M., Wang, T., Cohen-Or, D., Zhang, H., Chen, B.: Projective analysis for 3D shape segmentation. ACM Trans. Graph. 32(6), 192:1–192:12 (2013)

    MathSciNet  Google Scholar 

  26. Phong, B.T.: Illumination for computer generated pictures. Commun. ACM 18(6), 311–317 (1975)

    Article  Google Scholar 

  27. Li, H., Yang, Y., Chen, D., Lin, Z.: Optimization algorithm inspired deep neural network structure design. arXiv:1810.01638 (2018)

  28. Krahenbuhl, P., Koltun, V.: Effcient inference in fully connected crfs with gaussian edge potentials. In: Advances in Neural Information Processing Systems, pp. 109–117 (2011)

    Google Scholar 

  29. Wang, Y., Asafi, S., Van Kaick, O., Zhang, H., Cohen-Or, D., Chen, B.: Active co-analysis of a set of shapes. ACM Trans. Graph. 31(6), 165 (2012)

    Article  Google Scholar 

  30. Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 27 (2011)

    Article  Google Scholar 

  31. Shui, P., et al.: 3D shape segmentation based on viewpoint entropy and projective fully convolutional networks fusing multi-view features. In: The 24th International Conference on Pattern Recognition, pp. 1056–1061 (2018)

    Google Scholar 

  32. Nesterov, Y.: A method for unconstrained convex minimization problem with the rate of convergence 0(1/k2). Sov. Math. Doklady 27(2), 372–376 (1983)

    Google Scholar 

Download references

Acknowledgments

This work was supported by National Key R&D Program of China (2016YFC0303707).

Author information

Authors and Affiliations

  1. China University of Petroleum-Beijing, Beijing, 102200, China

    Likuan Qian, Yuanfeng Lian, Shuangyuan Wu & Jianbin Zhang

  2. CNPC Beijing Richfit Information Technology Co., LTD., Beijing, 102200, China

    Qian Wei

Authors
  1. Likuan Qian
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuanfeng Lian
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Qian Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shuangyuan Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jianbin Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yuanfeng Lian .

Editor information

Editors and Affiliations

  1. School of EECS, Peking University, Beijing, China

    Zhouchen Lin

  2. Institute of Automation, Chinese Academy of Sciences, Beijing, China

    Liang Wang

  3. Nanjing University of Science and Technology, Nanjing, China

    Jian Yang

  4. Xidian University, Xi’an, China

    Guangming Shi

  5. Institute of Automation, Chinese Academy of Sciences, Beijing, China

    Tieniu Tan

  6. Institute of Artificial Intelligence, Xi’an Jiaotong University, Xi’an, China

    Nanning Zheng

  7. Chinese Academy of Sciences, Beijing, China

    Xilin Chen

  8. Northwestern Polytechnical University, Xi’an, China

    Yanning Zhang

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Qian, L., Lian, Y., Wei, Q., Wu, S., Zhang, J. (2019). ODCN: Optimized Dilated Convolution Network for 3D Shape Segmentation. In: Lin, Z., et al. Pattern Recognition and Computer Vision. PRCV 2019. Lecture Notes in Computer Science(), vol 11859. Springer, Cham. https://doi.org/10.1007/978-3-030-31726-3_32

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-31726-3_32

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-31725-6

  • Online ISBN: 978-3-030-31726-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation