A Unified Feature Representation and Learning Framework for 3D Shape

MU Panpan; ZHANG Sanyuan; PAN Xiang; HONG Zhenjie

doi:10.1049/cje.2019.06.019

Volume 28 Issue 5

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2019 > 28(5): 993-999

MU Panpan, ZHANG Sanyuan, PAN Xiang, et al., “A Unified Feature Representation and Learning Framework for 3D Shape,” Chinese Journal of Electronics, vol. 28, no. 5, pp. 993-999, 2019, doi: 10.1049/cje.2019.06.019

Citation:

MU Panpan, ZHANG Sanyuan, PAN Xiang, et al., “A Unified Feature Representation and Learning Framework for 3D Shape,” Chinese Journal of Electronics, vol. 28, no. 5, pp. 993-999, 2019, doi: 10.1049/cje.2019.06.019

Citation:

PDF( 2083 KB)

A Unified Feature Representation and Learning Framework for 3D Shape

doi: 10.1049/cje.2019.06.019

1.
Art Design College, Zhejiang Gongshang University, Hangzhou 310018, China;
2.
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China;
3.
College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, China;
4.
School of Mathematics and Information Science, Wenzhou University, Wenzhou 325027, China

Funds: This work is supported by the National Natural Science Foundation of China (No.61871258) and the Natural Science Foundation of Zhejiang Province (No.LQ16F020007, No.LY19F020031).

More Information

Corresponding author: PAN Xiang (corresponding author) received the Ph.D.degree from the Department of Computer Science and Technology,Zhejiang University,China,in 2005.He is currently working as a professor of the College of Computer Science and Technology at Zhejiang University of Technology,China.His research interests include image and video processing and computer graphics.(Email:panx@zjut.edu.cn)
Received Date: 2017-06-21
Rev Recd Date: 2017-10-22
Publish Date: 2019-09-10

Abstract

Abstract

In conventional 3D shape retrieval and classification, they differentiate each other in their final stages. We propose a unified feature representation and learning framework for the instance-based shape retrieval and classification. Firstly, we render every 3D model in several directions and use the produced view-sets to represent the 3D models. In this way, both tasks can be tackled by measuring the distances between rendered views of 3D models. Secondly, we construct the viewsets as Symmetric positive definite matrices (SPDMs), which are points on a Riemannian manifold. Thus, the shape retrieval and classification tasks are reduced to a problem of measuring the distances between projected views and SPDMs. To solve this heterogeneous problem, we map them to a Hilbert space using a method of point-to-set matching. In this Hilbert space, the distances are surprisingly easy to calculate. Finally, we use a robust nearest-neighbor approach to unify the instancebased shape retrieval and classification. Our framework combines the state-of-the-art deep learning approaches with traditional mathematical optimization method, makes full use of both advantages, which is much more flexible than pure deep learning methods. Experimental results show the efficiency of our approach.
- Shape retrieval,
- Shape classification,
- Deep learning,
- Euclidean space,
- Riemannian manifold,
- Hilbert space,
- Metric learning

FullText(HTML)

References(21)

References

H. Su, S. Maji, E. Kalogerakis, et al., "Multi-view convolutional neural networks for 3d shape recognition", IEEE International Conference on Computer Vision, pp.945-953, 2015.

S. Bai, X. Bai, Z. Zhou, et al., "Gift:A real-time and scalable 3D shape search engine", IEEE Conference on Computer Vision and Pattern Recognition, pp.5023-5032, 2016.

X. Bai, S. Bai, Z. Zhu, et al., "3D shape matching via two layer coding", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.37, No.12, pp.2361-2373, 2015.

H. Tabia, H. Laga, D. Picard, et al., "Covariance descriptors for 3D shape matching and retrieval", IEEE Conference on Computer Vision and Pattern Recognition, pp. 4185-4192, 2014.

M. Ankerst, G. Kastenmuller, H.P. Kriegel, et al., "3D shape histograms for similarity search and classification in spatial databases", International Symposium on Spatial Databases, pp.207-226, 1999.

Z. Barutcuoglu and C. DeCoro, "Hierarchical shape classification using Bayesian aggregation", IEEE International Conf. on Shape Modeling and Applications, Page 44, 2006.

A.S. Mian, M. Bennamoun and R. Owens, "Three-dimensional model-based object recognition and segmentation in cluttered scenes", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.28, No.10, pp.1584-1601, 2006.

J. Sun, M. Ovsjanikov and L. Guibas, "A concise and provably informative multi-scale signature based on heat diffusion", Computer Graphics Forum, Vol.28, No.5, pp.1383-1392, 2009.

H. Pottmann, J. Wallner, Q.X. Huang, et al., "Integral invariants for robust geometry processing", Computer Aided Geometric Design, Vol.26, No.1, pp.37-60, 2009.

J. Novatnack and K. Nishino, "Scale-dependent/invariant local 3D shape descriptors for fully automatic registration of multiple sets of range images", European Conference on Computer Vision, pp.440-453, 2008.

R. Toldo, U. Castellani and A. Fusiello, "A bag of words approach for 3D object categorization", International Conference on Computer Vision/Computer Graphics Collaboration Techniques and Applications, pp.116-127, 2009.

L. Xie, R. Hong, B. Zhang, et al., "Image classification and retrieval are one", 5th ACM on International Conference on Multimedia Retrieval, pp.3-10, 2015.

O. Boiman, E. Shechtman and M. Irani, "In defense of nearestneighbor based image classification", IEEE Conference on Computer Vision and Pattern Recognition, pp.1-8, 2008.

Z. Huang, R. Wang, S. Shan, et al., "Learning euclideanto-riemannian metric for point-to-set classification", IEEE Conference on Computer Vision and Pattern Recognition, pp.1677-1684, 2014.

R. Wang, H. Guo, L.S. Davis, et al., "Covariance discriminative learning:A natural and efficient approach to image set classification", 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.2496-2503, 2012.

Z. Wu, S. Song, A. Khosla, et al., "3D shapenets:A deep representation for volumetric shapes", IEEE Conference on Computer Vision and Pattern Recognition, pp.1912-1920, 2015.

K. Chatfield, K. Simonyan, A. Vedaldi, et al., "Return of the devil in the details:Delving deep into convolutional nets", arXiv preprint, arXiv:14053531, 2014.

Y. Wen, K, Zhang, Z. Li, et al., "A discriminative feature learning approach for deep face recognition", European Conference on Computer Vision, pp.499-515, 2016.

M. Kazhdan, T. Funkhouser and S. Rusinkiewicz, "Rotation invariant spherical harmonic representation of 3D shape descriptors", Symp. on Geometry Processing, pp.156-164, 2003.

D.Y. Chen, X.P. Tian, Y.T. Shen, et al., "On visual similarity based 3D model retrieval", Computer Graphics Forum, Vol.22, No.3, pp.223-232, 2003.

P. Papadakis, I. Pratikakis, T. Theoharis, et al., "Panorama:A 3D shape descriptor based on panoramic views for unsupervised 3D object retrieval", International Journal of Computer Vision, Vol.89, No.2, pp.177-192, 2010.

Relative Articles

Supplements(0)

Cited By

Proportional views