3D Shape Recognition Based on Multimodal Relation Modeling

被引：0
|
作者：
Chen H.-N. [1 ]
Zhu Y.-Y. [1 ]
Zhao J.-Q. [1 ]
Tian Q. [2 ]
机构：
[1] College of Computer Science and Software Engineering, Shenzhen University, Shenzhen
[2] Huawei Technologies Co. Ltd., Shenzhen
来源：
Ruan Jian Xue Bao/Journal of Software | 2024年 / 35卷 / 05期
关键词：
3D shape recognition; multimodal learning; relation modeling;
D O I：
10.13328/j.cnki.jos.007026
中图分类号：
学科分类号：
摘要：
To make full use of the local spatial relation between point cloud and multi-view data to further improve the accuracy of 3D shape recognition, a 3D shape recognition network based on multimodal relation is proposed. Firstly, a multimodal relation module (MRM) is designed, which can extract the relation information between the local features of any point cloud and that of any multi-view to obtain the corresponding relation features. Then, a cascade pooling consisting of maximum pooling and generalized mean pooling is applied to process the relation tensor and obtain the global relation feature. There are two types of multimodal relation modules, which output the point-view relation feature and the view-point relation feature, respectively. The proposed gating module adopts a self-attention mechanism to find the relation information within the features so that the aggregated global features can be weighted to achieve the suppression of redundant information. Extensive experiments show that the MRM can make the network obtain stronger representational ability; the gating module can allow the final global feature more discriminative and boost the performance of the retrieval task. The proposed network achieves 93.8% and 95.0% classification accuracy, as well as 90.5% and 93.4% average retrieval precision on two standard 3D shape recognition datasets (ModelNet40 and ModelNet10k), respectively, which outperforms the existing works. © 2024 Chinese Academy of Sciences. All rights reserved.
引用
收藏
页码：2208 / 2219
页数：11
相关论文
共 23 条
  • [1] Maturana D, Scherer S., VoxNet: A 3D convolutional neural network for real-time object recognition, Proc. of the 2015 IEEE/RSJ Int’l Conf. on Intelligent Robots and Systems (IROS), pp. 922-928, (2015)
  • [2] Wu ZR, Song SR, Khosla A, Yu F, Zhang LG, Tang XO, Xiao JX., 3D ShapeNets: A deep representation for volumetric shapes, Proc. of the 2015 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1912-1920, (2015)
  • [3] Su H, Maji S, Kalogerakis E, Learned-Miller E., Multi-view convolutional neural networks for 3D shape recognition, Proc. of the 2015 IEEE Int’l Conf. on Computer Vision, pp. 945-953, (2015)
  • [4] Feng YF, Zhang ZZ, Zhao XB, Ji RR, Gao Y., GVCNN: Group-view convolutional neural networks for 3D shape recognition, Proc. of the 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, pp. 264-272, (2018)
  • [5] Charles RQ, Su H, Kaichun M, Guibas LJ., PointNet: Deep learning on point sets for 3D classification and segmentation, Proc. of the 2017 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 77-85, (2017)
  • [6] Qi CR, Yi L, Su H, Guibas LJ., PointNet++: Deep hierarchical feature learning on point sets in a metric space, Proc. of the 31st Int’l Conf. on Neural Information Processing Systems, pp. 5105-5114, (2017)
  • [7] Wang Y, Sun YB, Liu ZW, Sarma SE, Bronstein MM, Solomon JM., Dynamic graph CNN for learning on point clouds, ACM Trans. on Graphics, 38, 5, (2019)
  • [8] Li JX, Chen BM, Lee GH., SO-Net: Self-organizing network for point cloud analysis, Proc. of the 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, pp. 9397-9406, (2018)
  • [9] You HX, Feng YF, Ji RR, Gao Y., PVNet: A joint convolutional network of point cloud and multi-view for 3D shape recognition, Proc. of the 26th ACM Int’l Conf. on Multimedia, pp. 1310-1318, (2018)
  • [10] You HX, Feng YF, Zhao XB, Zou CQ, Ji RR, Gao Y., PVRNet: Point-view relation neural network for 3D shape recognition, Proc. of the 33rd AAAI Conf. on Artificial Intelligence and the 31st Innovative Applications of Artificial Intelligence Conf. and the 9th AAAI Symp. on Educational Advances in Artificial Intelligence, (2019)
123