Abstract
In a 3D shape retrieval system, when attempting to select the best view from many view images, the ability to project a 3D shape into related view images from multiple viewpoints is important. Furthermore, learning the best view from benchmark sketch datasets is one of the best approaches to acquire the best view of a 3D shape. In this paper, we propose a learning framework based on deep neural networks to obtain the best shape views. We apply transfer learning to obtain features, i.e., we use two Alex convolutional neural networks (CNNs) for feature extraction: one for the view images and the other for the sketches. Specifically, the connections to learn an automatic best-view selector for different types of 3D shapes are obtained through the proposed learning framework. We perform training on the Shape Retrieval Contest’s 2014 Sketch Track Benchmark (SHREC’14) to capture the related rules. Finally, we report experiments to demonstrate the feasibility of our approach. In addition, to better evaluate our proposed framework and show its superiority, we apply our proposed approach to a sketch-based model retrieval task, where it outperforms other state-of-the-art methods.
Similar content being viewed by others
References
Abadi M, Barham P, Chen J et al (2016) Tensorflow: a system for large-scale machine learning. Operating Systems Design and Implementation, pp 265–283
Chang AX, Funkhouser TA, Guibas LJ et al (2016) ShapeNet: an information-rich 3D model repository. arXiv:1512.03012
Chopra S, Hadsell R, Lecun Y (2005) Learning a similarity metric discriminatively, with application to face verification. In: IEEE conference on computer vision and pattern recognition, pp 539–546
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: IEEE conference on computer vision and pattern recognition. IEEE, pp 886–893
Daras P, Axenopoulos A (2010) A 3D shape retrieval framework supporting multimodal queries. Int J Comput Vis 89(2):229–247
Dutagaci H, Cheung CP, Godil A (2010) A benchmark for best view selection of 3D objects. In: Proceedings of the ACM workshop on 3D object retrieval, pp 45–50
Eitz M, Richter R, Boubekeur T, Hildebrand K, Alexa M (2012) Sketch-based shape retrieval. ACM Trans Graph 31:4,31:1–31:10
Eitz M, Hays J, Alexa M (2012) How do humans sketch objects? ACM Trans Graph 31(4):44:1–44:10
Ferrari V, Tuytelaars T, Gool LV (2006) Object detection by contour segment networks. In: Lecture notes in computer science. Springer, pp 14–28
Fu H, Cohen-Or D, Dror G, Sheffer A (2008) Upright orientation of man-made objects. In: Proceedings of ACM SIGGRAPH 2008, pp 42–50
Giorgi D, Mortara M, Spagnuolo M (2010) 3D shape retrieval based on best view selection. In: Proceedings of the ACM workshop on 3D object retrieval, pp 9–14
Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov PR (2012) Improving neural networks by preventing co-adaptation of feature detectors. Eprint arXiv:1207.0580
Kim S, Tai Y, Lee J et al (2017) Category-specific salient view selection via deep convolutional neural networks. Comput Graphics Forum 36(8):313–328
Ke C, Salman A (2011) Extracting speaker-specific information with a regularized siamese deep network. In: Proceedings of advances in neural information processing systems, pp 298–306
Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: International conference on neural information processing systems, pp 1097–1105
Laga H, Mortara M, Spagnuolo M (2013) Geometry and context for semantic correspondences and functionality recognition in man-made 3D shapes. ACM Trans Graph 32(5):150–160
Lee CH, Varshney A, Jacobs DW (2005) Mesh saliency. ACM Trans Graph 24(3):659–666
Lega H, Nakajima M (2008) Supervised learning of salient 2D views of 3D models. Journal of the Society for Art and Science 7(7):124–131
Li B, Lu Y, Li CC, Godil A, Schreck T, Aono M et al (2014) Large scale comprehensive 3D shape retrieval. In: 3DOR’15 Proceedings of the 7th Eurographics workshop on 3D object retrieval, pp 131–140
Li B, Lu Y, Godil A, Schreck T et al (2014) A comparison of methods for sketch-based 3D shape retrieval. Comput Vis Image Underst 119(2):57–80
Liu H, Zhang L, Huang H (2012) Web-image driven best views of 3D shapes. Vis Comput 28(3):279–287
Liu YJ, Luo X, Joneja A et al (2013) User-adaptive sketch-based 3-D CAD model retrieval. IEEE Trans Autom Sci Eng 10(3):783–795
Ma C, Yang X, Zhang C et al (2016) Sketch retrieval via local dense stroke features. Image Vis Comput 46(1):64–73
Mortara M, Spagnuolo M (2009) Semantics-driven best view of 3D shapes. Comput Graph 33(3):280–290
Shao T, Xu W, Yin K, Wang J, Zhou W, Guo B (2011) Discriminative sketch-base 3D model retrieval via robust shape matching. Computer Graphics Forum 30(7):2011–2020
Shilane P, Min P, Kazhdan M, Funkhouser T (2004) The Princeton shape benchmark. In: Shape modeling international conference. IEEE Computer Society, pp 167–178
Shtrom E, Leifman G, Tal A (2013) Saliency detection in large point sets. In: IEEE international conference on computer vision, pp 3591–3598
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556
Sivic J, Zisserman A (2003) Video Google: a text retrieval approach to object matching in videos. In: IEEE international conference on computer vision. IEEE Computer Society, pp 1470–1480
Srivastava N, Hinton G, Krizhevsky A et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958
Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions. In: IEEE conference on computer vision and pattern recognition. Boston, Massachusetts, USA, pp 1–9
Su H, Maji S, Kalogerakis E et al (2015) Multi-view convolutional neural networks for 3D shape recognition. In: International conference on computer vision. Santiago, Chile, pp 945–953
Tatsuma A, Koyanagi H, Aono M (2012) A large-scale shape benchmark for 3D object retrieval: Toyohashi shape benchmark. In: Proceedings of the 2012 Asia pacific signal and information processing association annual summit and conference (APSIPA ASC), pp 1–10
Wang F, Kang L, Li Y (2015) Sketch-based 3D shape retrieval using convolutional neural networks. In: The IEEE conference on computer vision and pattern recognition, pp 1875–1883
Xie J, Fang Y, Zhu F et al (2015) Deepshape: deep learned shape descriptor for 3D shape matching and retrieval. In: IEEE conference on computer vision and pattern recognition. Boston, Massachusetts, USA, pp 1275–1283
Xie J, Wang M, Fang Y et al (2016) Learned binary spectral shape descriptor for 3D shape correspondence. In: IEEE conference on computer vision and pattern recognition. Las Vegas, Nevada, USA, pp 3309–3317
Xie J, Dai G, Zhu F et al (2017) Learning Barycentric representations of 3D shapes for sketch-based 3D shape retrieval. In: IEEE conference on computer vision and pattern recognition. Honolulu, Hawaii, USA, pp 3615–3623
Yamauchi H, Saleem W, Yoshizawa S, Karni Z, Belyaev A et al (2006) Towards stable and salient multi-view representation of 3D shapes. In: IEEE international conference on shape modeling and applications, pp 40–50
Yih WT, Toutanova K, Platt JC, Meek C (2011) Learning discriminative projections for text similarity measures. In: CoNLL’11 Proceedings of the 15th conference on computational natural language learning, pp 247–256
Zhao L, Liang S, Jia J et al (2015) Learning best views of 3D shapes from sketch contour. Vis Comput 31(6):765–774
Zhou W, Jia JY (2017) SVM: Sketch-based 3D retrieval application using classification method. DEStech Transactions on Computer Science and Engineering
Zhou W, Jia JY (2019) A learning framework for shape retrieval based on multilayer perceptrons. Pattern Recogn Lett 117:119–130
Zhu F, Xie J, Fang Y (2016) Learning cross-domain neural networks for sketch-based 3D shape retrieval. In: AAAI’16 Proceedings of the 30th AAAI conference on artificial intelligence, pp 3683–3389
Acknowledgements
The authors appreciate the comments and suggestions of all the anonymous reviewers, whose comments helped us to significantly improve this paper. This work is supported in part by National Natural Science Foundation of China (NSFC Grant No. 61902003), The Key Research Projects of Central University of Basic Scientific Research Funds for Cross Cooperation (Grant No. 201510-02), Research Funds for the Doctoral Program of Higher Education of China (Grant No. 2013007211-0035), the Key Project in Science and Technology of Jilin Province of China (Grant No. 20140204088GX) and the Doctoral Scientific Research Foundation of Anhui Normal University.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhou, W., Jia, J. Training deep convolutional neural networks to acquire the best view of a 3D shape. Multimed Tools Appl 79, 581–601 (2020). https://doi.org/10.1007/s11042-019-08107-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-08107-w