Abstract
In order to enhance the discernment of features in view-based 3D shape recognition, we propose a joint convolutional neural network (CNN) learning model based on informative images. It learns deep features from intrinsic feature images and extrinsic 2D views, and generates a synthetic feature vector via weighted aggregation and refinement process, which has achieved remarkable improvement in non-rigid 3D shape classification. Our joint CNNs model contains three parts: the first part is the geometry-based feature generation unit. We provide a discriminative BoF (bag of features) image descriptor and construct CNN framework to learn the geometric features of the model. The second part is the view-based feature generation unit. We establish a parallel CNN to extract spatial features from optimized 2D views. The third part is a score generation and refinement unit, which automatically learns the weighted scores of geometric features and spatial features. Finally, the aggregated feature is refined in a CNN framework and serves as an informative shape descriptor for recognition task. The experimental results demonstrate that our deep features have the strong discerning ability. Thus, better performance and robustness can be obtained compared to state-of-the-art methods.
Similar content being viewed by others
References
Aubry M, Schlickewei U, Cremers D (2011) The wave kernel signature: A quantum mechanical approach to shape analysis. In: Proc. Computational Methods for the Innovative Design Electrical Devices, pp 1626–1633
Bai S, Bai X, Zhou Z, Zhang Z, Latechi LJ (2016) GIFT: A real-time and scalable 3D shape search engine. In: Proc. CVPR, pp. 5023–5032
Bronstein M. Kokkinos, I. (2010) Scale-invariant heat kernel signatures for non-rigid shape recognition. In: Proceedings of the CVPR, pp 1704–1711
Bronstein A, Bronstein M, Guibas LJ, Ovsjanikov M (2011) Shape Google: geometric words and expressions for invariant shape retrieval. ACM Trans Graph 30(1):1–22
Bu S, Cheng S, Liu Z, Han J (2014) Multimodal feature fusion for 3d shape recognition and retrieval. IEEE Multimed 21(4):38–46
Bu S, Liu Z, Han J, Wu J, Ji R (2014) Learning high-level feature by deep belief networks for 3-D model retrieval and recognition. IEEE Trans Multimed 24(16):2154–2167
Cai W, Wei Z (2020) PiiGAN: generative adversarial networks for pluralistic image. IEEE Access 8:48451–48463
Chen D-Y, Tian X-P, Shen Y-T, Ouhyoung M (2003) On visual similarity based 3d model retrieval. Comput Graph Forum 22:223–232. Wiley Online Library
Fang Y, Xie J, Dai G, Wang M, Fan Z, Xu T, Wang E (2015) 3D deep shape descriptor. In: Proc. of the 28th IEEE Conf. On CVPR, pp.2319–2328
Ghodrati H, Hamza AB (2016) Deep shape-aware descriptor for nonrigid 3D object retrieval. Int J Multimed Inf Retr 3:1–14
Ghodrati H, Hamza AB (2017) Nonrigid 3D shape retrieval using deep auto-encoders. Appl Intell 47:44–61
Guo H, Wang J, Gao Y, Li J, Lu H (2015) Graph-based characteristic view set extraction and matching for 3D model retrieval. Inf Sci 320:429–442
Guo H, Wang J, Gao Y et al (2016) Multi-view 3d object retrieval with deep embedding network. IEEE Trans Image Process 25(12):5526–5537
Han Z, Liu Z, Vong CM, Liu YS, Bu S, Han J, Chen CLP (2017) BoSCC: bag of spatial context correlations for spatially enhanced 3Dshape representation. IEEE Trans Image Process 26(8):3707–3720
Han L, Liu S, Yu B, Xu S (2020) Orientation-preserving spectral correspondence for 3D shape analysis. J Imaging Sci Technol 64(1):1–13
Laga H, Schreck T, Ferreira A, et al. (2011) Bag of words and local spectral descriptor for 3D partial shape retrieval. Proc. of the 4thEurographics Conf. on 3D Object Retrieval, Llandudno, April 10, 41–48
Leng B, Cheng Z, Zhou XC (2018) Learning discriminative 3D shape representations by view discerning networks. IEEE Trans Vis Comput Graph
Litman R, Bronstein A, Bronstein M, Castellani U (2014) Supervised learning of bag-of-features shape descriptors using sparse coding. Comput Graph Forum 33(5):127–136
Luciano L, Hamza AB (2017) Deep learning with geodesic moments for 3D shape classification. Pattern Recog Lett
Masoumi M, Hamza AB (2017) Spectral shape classification: a deep learning approach. J Vis Commun Image Represent 43:198–211
Masoumi M, Li C, Hamza AB (2016) A spectral graph wavelet approach for nonrigid 3D shape retrieval. Pattern Recogn Lett 83:339–348
Matsuda T, Furuya T, Ohbuchi R (2015) Lightweight Binary Voxel Shape Features for 3D Data Matching and Retrieval. In: Multimedia BigData, pp. 100–107
Maturana D, Scherer S (2015) VoxNet: a 3D convolutional neural network for real-Time object recognition. In: Proc. International Conference on Intelligent Robots & Systems (IROS)
Mohamed W, Hamza AB (2016) Deformable 3D shape retrieval using a spectral geometric descriptor. Appl Intell 45(2):2213–2229
Ovsjanikov M, Bronstein A, Bronstein, M., Guibas LJ (2009) Shape Google: A computer vision approach to isometry invariant shape retrieval. In: Proc. 2009 IEEE 12th Int Conf Comput Vis Workshops, pp. 320–327
Papadakis P, Pratikakis I, Theoharis T, Perantonis S (2010) Panorama: a 3d shape descriptor based on panoramic views for unsupervised 3d object retrieval. J Comput Vis 89(2):177–192
Qi CR, Su H, Mo K, Guibas LJ (2017) Pointnet: deep learning on point sets for 3d classification and segmentation. In Proc. CVPR
Qi CR, Yi L, Su H, Guibas LJ (2018) PointNet++: deep hierarchical feature learning on point sets in a metric space. In Proc. CVPR
Reuter M, Wolter F, Peinecke N (2006) Laplace-Beltrami spectra as ‘Shape-DNA’ of surfaces and solids. Comput Aided Des 38(4):342–366
Rustamov R (n.d.) Laplace-Beltrami eigenfunctions for deformation invariant shape representation. In: Proc. Symp. Geometry Processing, pp 225–233.
Shi BG, Bai S, Zhou Z et al (2015) DeepPano: deep panoramic representation for 3D shape recognition. IEEE Signal Process Lett 22(12):2339–2343
Sinha A, Bai J, Ramani K (2016) Deep learning 3D shape surfaces using geometry images. In: Proceedings of the European Conference on Computer Vision. Amsterdam, 223–240.
Su H, Maji S, Kalogerakis E, Learned-Miller E (2015) Multi-view convolutional neural networks for 3d shape recognition. In: Proc.ICCV
Sun J, Ovsjanikov M, Guibas L (2009) A concise and provably informative multi-scale signature based on heat diffusion. Comput Graph Forum 28(5):1383–1392
Toldo R, Castellani U, Fusiello A (2009) Visual vocabulary signature for 3D object retrieval and partial matching. In: Proc. 2nd Eurograph Conf 3D Object Retrieval, pp. 21–28
Verma N, Boyer E, Verbee J (2018) FeaStNet: Feature-Steered graph convolutions for 3D shape analysis. In: Proc. CVPR, pp. 2598–2606
Wan L, Zou C, Zhang H (2017) Full and partial shape similarity through sparse descriptor reconstruction. Vis Comput 33(12):1497–1509
Wang Z, Zou C, Cai W (2020) Small sample classification of Hyperspectral remote sensing images based on sequential joint Deeping learning model. IEEE Access 8:71353–71363. https://doi.org/10.1109/ACCESS.2020.2986267
Xie J, Fang Y, Zhu F (2016) Deep Shape: deep Learned shape descriptor for 3D shape matching and retrieval. Comput Vis Pattern Recog
Ye J, Yu Y (2015) A fast modal space transform for robust non rigid shape retrieval. Vis Comput 32(5):553–568
Yi L, Zhao W, Wang H, Sung M, Guibas L (2019) StructureNet: hierarchical graph networks for 3D shape generation. In Proc. Siggraph Asia
You H, Tian S, Yu L, Lv Y (2020) Pixel-level remote sensing image recognition based on bidirectional word vectors. IEEE Trans Geosci Remote Sens 58(2):1281–1293
Yu F, Liu K, Zhang Y, Zhu C, Xu K (2019) PartNet: a large-scale benchmark for fine-grained and hierarchical part-level 3D object understanding. In: Proc. CVPR
Zhou Y, Zeng F, Qian J, Xiang Y, Feng Z (2019) FVCNN: Fusion View Convolutional Neural Networks for Non-rigid 3D Shape Classification and Retrieval, International Conference on Image and Graphics, 566–581, Beijing, P.R. China, 8.23–8.25
Acknowledgements
We would like to thank the anonymous reviewers for their helpful comments. The research presented in this paper is supported by a grant from NSFC (61702246), grants from research project of Liaoning province (2019lsktyb-084, 2020JH4/10100045) and a fund of Dalian Science and Technology (2019J12GX038).
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
Han, L., Piao, J., Tong, Y. et al. Deep learning for non-rigid 3D shape classification based on informative images. Multimed Tools Appl 80, 973–992 (2021). https://doi.org/10.1007/s11042-020-09764-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-09764-y