skip to main content
10.1145/3293353.3293426acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicvgipConference Proceedingsconference-collections
research-article

SplineNet: B-spline neural network for efficient classification of 3D data

Published: 03 May 2020 Publication History

Abstract

Advancement in the field of 3D capture, owing to use of consumer depth sensors, has reinvigorated the research interest for scalable shape classification and recognition algorithms. Majority of recent deep learning pipelines for 3D shapes uses volumetric representation, extending the concept of 2D convolution to 3D domain. Nevertheless, the volumetric representation poses a serious computational disadvantage as most of the voxel grids are empty and results in redundant computation. Moreover, a 3D shape is determined by its surface and hence performing convolutions on the voxels inside the shape is sheer wastage of computation.
In this paper, we focus on constructing a novel, fast and robust characterization of 3D shapes that accounts for local geometric variations as well as global structure. We built up on the learning scheme of [17] by introducing sets of B-spline surfaces instead of point filters, in order to sense complex geometrical structures (large curvature variations). The locations of these surfaces are initialized over the voxel space and are learned during training phase. We propose SplineNet, a deep network consisting of B-spline surfaces for classification of input 3D data represented in volumetric grid. We derive analytical solutions for updates of B-spline surfaces during back propagation. We show results on publicly available dataset and achieve superior performance as compared to state-of-the-art method.

References

[1]
Varun Arvind, Anthony Costa, Marcus Badgeley, Samuel Cho, and Eric Oermann. 2017. Wide and deep volumetric residual networks for volumetric image classification. arXiv preprint arXiv:1710.01217 (2017).
[2]
Mathieu Aubry, Ulrich Schlickewei, and Daniel Cremers. 2011. The wave kernel signature: A quantum mechanical approach to shape analysis. In Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on. IEEE, 1626--1633.
[3]
Davide Boscaini, Jonathan Masci, Emanuele Rodolà, and Michael Bronstein. 2016. Learning shape correspondence with anisotropic convolutional neural networks. In Advances in Neural Information Processing Systems. 3189--3197.
[4]
André Brock, Theodore Lim, James M Ritchie, and Nick Weston. 2016. Generative and Discriminative Voxel Modeling with Convolutional Neural Networks. CoRR abs/1608.04236 (2016). (2016).
[5]
Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. 2013. Spectral Networks and Locally Connected Networks on Graphs. CoRR abs/1312.6203 (2013). arXiv:1312.6203 http://arxiv.org/abs/1312.6203
[6]
Yang Chen and Gérard Medioni. 1992. Object modelling by registration of multiple range images. Image and vision computing 10, 3 (1992), 145--155.
[7]
Chin Seng Chua and Ray Jarvis. 1997. Point signatures: A new representation for 3d object recognition. International Journal of Computer Vision 25, 1 (1997), 63--85.
[8]
Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. CoRR abs/1606.09375 (2016). arXiv:1606.09375 http://arxiv.org/abs/1606.09375
[9]
Timothy Gatzke, Cindy Grimm, Michael Garland, and Steve Zelinka. 2005. Curvature maps for local shape comparison. In Shape Modeling and Applications, 2005 International Conference. IEEE, 244--253.
[10]
Dirk Holz and Sven Behnke. 2013. Fast range image segmentation and smoothing using approximate surface reconstruction and region growing. In Intelligent autonomous systems 12. Springer, 61--73.
[11]
Andrew E Johnson and Martial Hebert. 1999. Using spin images for efficient object recognition in cluttered 3D scenes. IEEE Transactions on Pattern Analysis & Machine Intelligence 5 (1999), 433--449.
[12]
Asako Kanezaki, Yasuyuki Matsushita, and Yoshifumi Nishida. 2016. Rotation-Net: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints. arXiv preprint arXiv:1603.06208 (2016).
[13]
Roman Klokov and Victor Lempitsky. 2017. Escape from cells: Deep kd-networks for the recognition of 3d point cloud models. In Computer Vision (ICCV), 2017 IEEE International Conference on. IEEE, 863--872.
[14]
Marcel Körtgen, Gil-Joo Park, Marcin Novotni, and Reinhard Klein. 2003. 3D shape matching with 3D shape contexts. In The 7th central European seminar on computer graphics, Vol. 3. Budmerice, 5--17.
[15]
Ryan Lambert. 2018. Capsule Nets for Content Based 3D Model Retrieval. (2018). https://github.com/Ryanglambert/3d_model_retriever
[16]
Yann Lecun, LÃl'on Bottou, Yoshua Bengio, and Patrick Haffner. 1998. Gradient-based learning applied to document recognition. In Proceedings of the IEEE. 2278--2324.
[17]
Yangyan Li, Soeren Pirk, Hao Su, Charles R Qi, and Leonidas J Guibas. 2016. Fpnn: Field probing neural networks for 3d data. In Advances in Neural Information Processing Systems. 307--315.
[18]
Shikun Liu, Lee Giles, and Alexander Ororbia. 2018. Learning a Hierarchical Latent-Variable Model of 3D Shapes. In 2018 International Conference on 3D Vision (3DV). IEEE, 542--551.
[19]
David G Lowe. 2004. Distinctive image features from scale-invariant keypoints. International journal of computer vision 60, 2 (2004), 91--110.
[20]
Jonathan Masci, Davide Boscaini, Michael Bronstein, and Pierre Vandergheynst. 2015. Geodesic convolutional neural networks on riemannian manifolds. In Proceedings of the IEEE international conference on computer vision workshops. 37--45.
[21]
Jonathan Masci, Emanuele Rodolà, Davide Boscaini, Michael M Bronstein, and Hao Li. 2016. Geometric deep learning. In SIGGRAPH ASIA 2016 Courses. ACM, 1.
[22]
Daniel Maturana and Sebastian Scherer. 2015. Voxnet: A 3d convolutional neural network for real-time object recognition. In Intelligent Robots and Systems (IROS), 2015 IEEE/RSJ International Conference on. IEEE, 922--928.
[23]
Michela Mortara, Giuseppe Patané, Michela Spagnuolo, Bianca Falcidieno, and Jarek Rossignac. 2004. Blowing bubbles for multi-scale analysis and decomposition of triangle meshes. Algorithmica 38, 1 (2004), 227--248.
[24]
Helmut Pottmann, Johannes Wallner, Qi-Xing Huang, and Yong-Liang Yang. 2009. Integral invariants for robust geometry processing. Computer Aided Geometric Design 26, 1 (2009), 37--60.
[25]
Charles Ruizhongtai Qi, Hao Su, Kaichun Mo, and Leonidas J. Guibas. 2016. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. CoRR abs/1612.00593 (2016). arXiv:1612.00593 http://arxiv.org/abs/1612.00593
[26]
Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J. Guibas. 2017. PointNet+ +: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. CoRR abs/1706.02413 (2017). arXiv:1706.02413 http://arxiv.org/abs/1706.02413
[27]
Raif M Rustamov. 2007. Laplace-Beltrami eigenfunctions for deformation invariant shape representation. In Proceedings of the fifth Eurographics symposium on Geometry processing. Eurographics Association, 225--233.
[28]
Nima Sedaghat, Mohammadreza Zolfaghari, and Thomas Brox. 2016. Orientation-boosted Voxel Nets for 3D Object Recognition. CoRR abs/1604.03351 (2016). arXiv:1604.03351 http://arxiv.org/abs/1604.03351
[29]
Baoguang Shi, Song Bai, Zhichao Zhou, and Xiang Bai. 2015. Deeppano: Deep panoramic representation for 3-d shape recognition. IEEE Signal Processing Letters 22, 12 (2015), 2339--2343.
[30]
Dirk Smeets, Jeroen Hermans, Dirk Vandermeulen, and Paul Suetens. 2012. Isometric deformation invariant 3D shape recognition. Pattern Recognition 45, 7 (2012), 2817--2831.
[31]
Hang Su, Subhransu Maji, Evangelos Kalogerakis, and Erik Learned-Miller. 2015. Multi-view convolutional neural networks for 3d shape recognition. In Proceedings of the IEEE international conference on computer vision. 945--953.
[32]
Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, and Xin Tong. 2017. O-cnn: Octree-based convolutional neural networks for 3d shape analysis. ACM Transactions on Graphics (TOG) 36, 4 (2017), 72.
[33]
Jiajun Wu, Yifan Wang, Tianfan Xue, Xingyuan Sun, Bill Freeman, and Josh Tenenbaum. 2017. Marrnet: 3d shape reconstruction via 2.5 d sketches. In Advances in neural information processing systems. 540--550.
[34]
Jiajun Wu, Chengkai Zhang, Tianfan Xue, Bill Freeman, and Josh Tenenbaum. 2016. Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling. In Advances in Neural Information Processing Systems. 82--90.
[35]
Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1912--1920.
[36]
Sameh M Yamany and Aly A Farag. 1999. Free-form surface registration using surface signatures. In Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on, Vol. 2. IEEE, 1098--1104.
[37]
Yaoqing Yang, Chen Feng, Yiru Shen, and Dong Tian. 2018. Foldingnet: Point cloud auto-encoder via deep grid deformation. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Vol. 3.

Index Terms

  1. SplineNet: B-spline neural network for efficient classification of 3D data

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Other conferences
      ICVGIP '18: Proceedings of the 11th Indian Conference on Computer Vision, Graphics and Image Processing
      December 2018
      659 pages
      ISBN:9781450366151
      DOI:10.1145/3293353
      Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 03 May 2020

      Permissions

      Request permissions for this article.

      Check for updates

      Qualifiers

      • Research-article
      • Research
      • Refereed limited

      Conference

      ICVGIP 2018

      Acceptance Rates

      Overall Acceptance Rate 95 of 286 submissions, 33%

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • 0
        Total Citations
      • 78
        Total Downloads
      • Downloads (Last 12 months)18
      • Downloads (Last 6 weeks)1
      Reflects downloads up to 16 Jan 2025

      Other Metrics

      Citations

      View Options

      Login options

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Media

      Figures

      Other

      Tables

      Share

      Share

      Share this Publication link

      Share on social media