Abstract
The current methods for multi-view-based 3D object recognition have the problem of losing the correlation between views and rendering 3D objects with multi-view redundancy. This makes it difficult to improve recognition performance and unnecessarily increases the computational cost and running time of the network. Especially in the case of limited computing resources, the recognition performance is further affected. Our study developed an optimal viewset pooling transformer (OVPT) method for efficient and accurate 3D object recognition. The OVPT method constructs the optimal viewset based on information entropy to reduce the redundancy of the multi-view scheme. We used convolutional neural network (CNN) to extract the multi-view low-level local features of the optimal viewset. Embedding class token into the headers of multi-view low-level local features and splicing with position encoding generates local-view token sequences. This sequence was trained parallel with a pooling transformer to generate a local view information token sequence. At the same time, the global class token captured the global feature information of the local view token sequence. The two were aggregated next into a single compact 3D global feature descriptor. On two public benchmarks, ModelNet10 and ModelNet40, for each 3D object we only need a smaller number of optimal viewsets, achieving an overall recognition accuracy (OA) of 99.33% and 97.48%, respectively. Compared with other deep learning methods, our method still achieves state-of-the-art performance with limited computational resources. Our source code is available at https://github.com/shepherds001/OVPT.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Liang, Z., et al.: Stereo matching using multi-level cost volume and multi-scale feature constancy. IEEE Trans. Pattern Anal. Mach. Intell. 43(1), 300–315 (2021). https://doi.org/10.1109/TPAMI.2019.2928550
Li, Y., et al.: Deep learning for lidar point clouds in autonomous driving: a review. IEEE Trans. Neural Netw. Learn. Syst. 32(8), 3412–3432 (2021). https://doi.org/10.1109/TNNLS.2020.3015992
Kästner, L., Frasineanu, V.C., Lambrecht, J.: A 3D-deep-learning-based augmented reality calibration method for robotic environments using depth sensor data. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 1135–1141 (2020). https://doi.org/10.1109/ICRA40945.2020.9197155
Lee, D., et al.: Large-scale localization datasets in crowded indoor spaces. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3226–3235 (2021). https://doi.org/10.1109/CVPR46437.2021.00324
Maturana, D., Scherer, S.: Voxnet: a 3D convolutional neural network for real-time object recognition. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 922–928 (2015). https://doi.org/10.1109/IROS.2015.7353481
Wu, Z., et al.: 3D shapenets: a deep representation for volumetric shapes. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1912–1920 (2015). https://doi.org/10.1109/CVPR.2015.7298801
Riegler, G., Ulusoy, A.O., Geiger, A.: Octnet: learning deep 3D representations at high resolutions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6620–6629 (2017). https://doi.org/10.1109/CVPR.2017.701
Wang, P.S., Liu, Y., Guo, Y.X., Sun, C.Y., Tong, X.: O-cnn: octree-based convolutional neural networks for 3d shape analysis. ACM Trans. Graph. 36(4) (2017). https://doi.org/10.1145/3072959.3073608
Klokov, R., Lempitsky, V.: Escape from cells: Deep kd-networks for the recognition of 3D point cloud models. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 863–872 (2017). https://doi.org/10.1109/ICCV.2017.99
Zeng, W., Gevers, T.: 3DContextNet: K-d tree guided hierarchical learning of point clouds using local and global contextual cues. In: Leal-Taixé, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11131, pp. 314–330. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11015-4_24
Le, T., Duan, Y.: Pointgrid: a deep network for 3D shape understanding. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9204–9214 (2018). https://doi.org/10.1109/CVPR.2018.00959
Meng, H.Y., Gao, L., Lai, Y.K., Manocha, D.: Vv-net: voxel vae net with group convolutions for point cloud segmentation. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 8499–8507 (2019). https://doi.org/10.1109/ICCV.2019.00859
Charles, R.Q., Su, H., Kaichun, M., Guibas, L.J.: Pointnet: Deep learning on point sets for 3D classification and segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 77–85 (2017). https://doi.org/10.1109/CVPR.2017.16
Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017). https://proceedings.neurips.cc/paper/2017/file/d8bf84be3800d12f74d8b05e9b89836f-Paper.pdf
Jiang, M., Wu, Y., Zhao, T., Zhao, Z., Lu, C.: Pointsift: a sift-like network module for 3D point cloud semantic segmentation (2018). https://doi.org/10.48550/ARXIV.1807.00652
Zhao, H., Jiang, L., Fu, C.W., Jia, J.: Pointweb: enhancing local neighborhood features for point cloud processing. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5560–5568 (2019). https://doi.org/10.1109/CVPR.2019.00571
Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., Lu, H.: Dual attention network for scene segmentation. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3141–3149 (2019). https://doi.org/10.1109/CVPR.2019.00326
Feng, M., Zhang, L., Lin, X., Gilani, S.Z., Mian, A.: Point attention network for semantic segmentation of 3D point clouds. Pattern Recogn. 107, 107446 (2020). https://doi.org/10.1016/j.patcog.2020.107446, https://www.sciencedirect.com/science/article/pii/S0031320320302491
Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph cnn for learning on point clouds. ACM Trans. Graph. 38(5) (2019). https://doi.org/10.1145/3326362
Zhang, K., Hao, M., Wang, J., de Silva, C.W., Fu, C.: Linked dynamic graph cnn: learning on point cloud via linking hierarchical features (2019). https://doi.org/10.48550/ARXIV.1904.10014, https://arxiv.org/abs/1904.10014
Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3D shape recognition. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 945–953 (2015). https://doi.org/10.1109/ICCV.2015.114
Wang, C., Pelillo, M., Siddiqi, K.: Dominant set clustering and pooling for multi-view 3d object recognition (2019). https://doi.org/10.48550/ARXIV.1906.01592, https://arxiv.org/abs/1906.01592
Feng, Y., Zhang, Z., Zhao, X., Ji, R., Gao, Y.: Gvcnn: group-view convolutional neural networks for 3D shape recognition. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 264–272 (2018). https://doi.org/10.1109/CVPR.2018.00035
Kanezaki, A., Matsushita, Y., Nishida, Y.: Rotationnet: joint object categorization and pose estimation using multiviews from unsupervised viewpoints. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5010–5019 (2018). https://doi.org/10.1109/CVPR.2018.00526
Esteves, C., Xu, Y., Allec-Blanchette, C., Daniilidis, K.: Equivariant multi-view networks. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 1568–1577 (2019). https://doi.org/10.1109/ICCV.2019.00165
Han, Z.: 3d2seqviews: aggregating sequential views for 3D global feature learning by CNN with hierarchical attention aggregation. IEEE Trans. Image Process. 28(8), 3986–3999 (2019). https://doi.org/10.1109/TIP.2019.2904460
He, X., Huang, T., Bai, S., Bai, X.: View n-gram network for 3D object retrieval. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 7514–7523 (2019). https://doi.org/10.1109/ICCV.2019.00761
Yang, Z., Wang, L.: Learning relationships for multi-view 3D object recognition. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 7504–7513 (2019). https://doi.org/10.1109/ICCV.2019.00760
Chen, S., Zheng, L., Zhang, Y., Sun, Z., Xu, K.: Veram: view-enhanced recurrent attention model for 3D shape classification. IEEE Trans. Visualization Comput. Graph. 25(12), 3244–3257 (2019). https://doi.org/10.1109/TVCG.2018.2866793
Liu, A.A., et al.: Hierarchical multi-view context modelling for 3D object classification and retrieval. Inf. Sci. 547, 984–995 (2021). https://doi.org/10.1016/j.ins.2020.09.057, https://www.sciencedirect.com/science/article/pii/S0020025520309671
Lin, C., Li, C., Liu, Y., Chen, N., Choi, Y.K., Wang, W.: Point2skeleton: learning skeletal representations from point clouds. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 4275–4284 (2021). https://doi.org/10.1109/CVPR46437.2021.00426
Liu, M., Zhang, X., Su, H.: Meshing point clouds with predicted intrinsic-extrinsic ratio guidance. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 68–84. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58598-3_5
Rakotosaona, M.J., Guerrero, P., Aigerman, N., Mitra, N., Ovsjanikov, M.: Learning delaunay surface elements for mesh reconstruction. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22–31 (2021). https://doi.org/10.1109/CVPR46437.2021.00009
Shannon, C.E.: A mathematical theory of communication. Bell Syst. Tech. J. 27(3), 379–423 (1948). https://doi.org/10.1002/j.1538-7305.1948.tb01338.x
Vázquez, P.P., Feixas, M., Sbert, M., Heidrich, W.: Viewpoint selection using viewpoint entropy. In: VMV, vol. 1, pp. 273–280. Citeseer (2001)
Vázquez, P.P., Feixas, M., Sbert, M., Heidrich, W.: Automatic view selection using viewpoint entropy and its application to image-based modelling. Comput. Graph. Forum 22(4), 689–700. https://doi.org/10.1111/j.1467-8659.2003.00717.x, https://onlinelibrary.wiley.com/doi/abs/10.1111/j.1467-8659.2003.00717.x
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009). https://doi.org/10.1109/CVPR.2009.5206848
Dosovitskiy, A., et al.: An image is worth 16\(\times \)16 words: transformers for image recognition at scale (2020). https://doi.org/10.48550/ARXIV.2010.11929, https://arxiv.org/abs/2010.11929
Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization (2016). https://doi.org/10.48550/ARXIV.1607.06450, https://arxiv.org/abs/1607.06450
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016). https://doi.org/10.1109/CVPR.2016.90
Hendrycks, D., Gimpel, K.: Gaussian error linear units (gelus) (2016). https://doi.org/10.48550/ARXIV.1606.08415, https://arxiv.org/abs/1606.08415
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261–2269 (2017). https://doi.org/10.1109/CVPR.2017.243
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2014). https://doi.org/10.48550/ARXIV.1412.6980, https://arxiv.org/abs/1412.6980
Xu, Y., Zheng, C., Xu, R., Quan, Y., Ling, H.: Multi-view 3D shape recognition via correspondence-aware deep learning. IEEE Trans. Image Process. 30, 5299–5312 (2021). https://doi.org/10.1109/TIP.2021.3082310
Chen, S., Yu, T., Li, P.: Mvt: multi-view vision transformer for 3D object recognition (2021). https://doi.org/10.48550/ARXIV.2110.13083, https://arxiv.org/abs/2110.13083
Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers & distillation through attention. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 10347–10357. PMLR (2021). https://proceedings.mlr.press/v139/touvron21a.html
Yu, T., Meng, J., Yuan, J.: Multi-view harmonized bilinear network for 3D object recognition. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 186–194 (2018). https://doi.org/10.1109/CVPR.2018.00027
Acknowledgments
The fnancial support for this work was sponsored by Natural Science Foundation of Shanghai under Grant No. 19ZR1435900.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, W., Chen, G., Zhou, H., Wang, X. (2023). OVPT: Optimal Viewset Pooling Transformer for 3D Object Recognition. In: Wang, L., Gall, J., Chin, TJ., Sato, I., Chellappa, R. (eds) Computer Vision – ACCV 2022. ACCV 2022. Lecture Notes in Computer Science, vol 13841. Springer, Cham. https://doi.org/10.1007/978-3-031-26319-4_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-26319-4_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26318-7
Online ISBN: 978-3-031-26319-4
eBook Packages: Computer ScienceComputer Science (R0)