|
|
GridNet: efficiently learning deep hierarchical representation for 3D point cloud understanding |
Huiqun WANG, Di HUANG( ), Yunhong WANG |
Laboratory of Intelligent Recognition and Image Processing, School of Computer Science and Engineering, Beihang University, Beijing 100191, China |
|
|
Abstract In this paper, we propose a novel and effective approach, namely GridNet, to hierarchically learn deep representation of 3D point clouds. It incorporates the ability of regular holistic description and fast data processing in a single framework, which is able to abstract powerful features progressively in an efficient way.Moreover, to capture more accurate internal geometry attributes, anchors are inferred within local neighborhoods, in contrast to the fixed or the sampled ones used in existing methods, and the learned features are thus more representative and discriminative to local point distribution. GridNet delivers very competitive results compared with the state of the art methods in both the object classification and segmentation tasks.
|
Keywords
3D point clouds
deep representations
|
Corresponding Author(s):
Di HUANG
|
Just Accepted Date: 28 June 2020
Issue Date: 11 June 2021
|
|
1 |
D Maturana, S Scherer. Voxnet: a 3D convolutional neural network for real-time object recognition. In: Proceedings of the IEEE International Conference on Intelligent Robots and Systems. 2015, 922–928
https://doi.org/10.1109/IROS.2015.7353481
|
2 |
A Brock, T Lim, J Ritchie, N Weston. Generative and discriminative voxel modeling with convolutional neural networks. In: Proceedings of Neural Information Processing Conference: 3D Deep Learning. 2016
|
3 |
V Hegde, R Zadeh. Fusionnet: 3D object classification using multiple data representations. 2016, arXiv preprint arXiv:1607.05695
|
4 |
H Su, S Maji, E Kalogerakis, E Learned-Miller.Multi-view convolutional neural networks for 3D shape recognition. In: Proceedings of the IEEE International Conference on Computer Vision. 2015, 945–953
https://doi.org/10.1109/ICCV.2015.114
|
5 |
T Yu, J Meng, J Yuan. Multi-view harmonized bilinear network for 3D object recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 186–194
https://doi.org/10.1109/CVPR.2018.00027
|
6 |
Y, Feng Z Zhang, X Zhao, R Ji, Y. GaoGVCNN: group-view convolutional neural networks for 3D shape recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 264–272
https://doi.org/10.1109/CVPR.2018.00035
|
7 |
C Qi, H Su, M Nießner, A Dai, M Yan, L Guibas. Volumetric and multiview cnns for object classification on 3D data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, 5648–5656
https://doi.org/10.1109/CVPR.2016.609
|
8 |
A Kanezaki, Y Matsushita, Y Nishida. Rotationnet: joint object categorization and pose estimation using multiviews from unsupervised viewpoints. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition. 2018, 5010–5019
https://doi.org/10.1109/CVPR.2018.00526
|
9 |
Y Zhou, O Tuzel. Voxelnet: end-to-end learning for point cloud based 3D object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 4490–4499
https://doi.org/10.1109/CVPR.2018.00472
|
10 |
Y Li, R, Bu M Sun, B Chen. Pointcnn: convolution on χ-transformed points. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2018, 828–838
|
11 |
C Qi, H Su, K Mo, L Guibas. Pointnet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017, 77–85
|
12 |
T Le, Y Duan. Pointgrid: a deep network for 3D shape understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 9204–9214
https://doi.org/10.1109/CVPR.2018.00959
|
13 |
X Ye, J Li, H Huang, L Du, X Zhang. 3D recurrent neural networks with context fusion for point cloud semantic segmentation. In: Proceedings of European Conference on Computer Vision. 2018, 415–430
https://doi.org/10.1007/978-3-030-01234-2_25
|
14 |
C, Qi L Yi, H Su, L Guibas. Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017, 5099–5108
|
15 |
Z Wu, S Song, A Khosla, F, Yu L Zhang, X Tang, J Xiao. 3D shapenets: a deep representation for volumetric shapes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015, 1912–1920
|
16 |
L Yi, V Kim, D Ceylan, I, Shen M Yan, H Su, C Lu, Q Huang, Sheffer Alla, Guibas Leonidas, et al.A scalable active framework for region annotation in 3D shape collections. ACM Transactions on Graphics, 2016, 35(6): 1–12
https://doi.org/10.1145/2980179.2980238
|
17 |
D Rethage, J Wald, J Sturm, N Navab, F Tombari. Fully-convolutional point networks for large-scale point clouds. In: Proceedings of European Conference on Computer Vision. 2018, 625–640
https://doi.org/10.1007/978-3-030-01225-0_37
|
18 |
Z Liu, H Tang, Y Lin, S Han. Point-voxel CNN for efficient 3D deep learning. In: Proceedings of Annual Conference on Neural Information Processing Systems. 2019, 963–973
|
19 |
C Szegedy, W Liu, Y Jia, P Sermanet, S Reed, D Anguelov, D Erhan, V Vanhoucke, A Rabinovich. Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014, 1–9
https://doi.org/10.1109/CVPR.2015.7298594
|
20 |
K He, X Zhang, S Ren, J. SunDeep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, 770–778
https://doi.org/10.1109/CVPR.2016.90
|
21 |
R Klokov, V Lempitsky. Escape from cells: deep KD-networks for the recognition of 3D point cloud models. In: Proceedings of the IEEE International Conference on Computer Vision. 2017, 863–872
https://doi.org/10.1109/ICCV.2017.99
|
22 |
P Wang, Y, Liu Y, Guo C Sun, X. TongO-CNN: octree-based convolutional neural networks for 3D shape analysis. ACM Transactions on Graphics, 2017, 36(4): 1–11
https://doi.org/10.1145/3072959.3073608
|
23 |
M Tatarchenko, A Dosovitskiy, T Brox. Octree generating networks: efficient convolutional architectures for high-resolution 3D outputs. In: Proceedings of the IEEE International Conference on Computer Vision. 2017, 2107–2115
https://doi.org/10.1109/ICCV.2017.230
|
24 |
G Riegler, A Ulusoy, A Geiger. Octnet: learning deep 3D representations at high resolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017, 6620–6629
https://doi.org/10.1109/CVPR.2017.701
|
25 |
L Yi, H Su, X Guo, L Guibas. Syncspeccnn: synchronized spectral CNN for 3D shape segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017, 6584–6592
https://doi.org/10.1109/CVPR.2017.697
|
26 |
S Zhi, Y Liu, X Li, Y Guo. Lightnet: a lightweight 3D convolutional neural network for real-time 3D object recognition. In: Proceedings of the Workshop on 3D Object Retrieval. 2017, 9–16
|
27 |
Y Li, S Pirk, H Su, C Qi, L Guibas. FPNN: field probing neural networks for 3D data. In: Proceedings of the 30th International Conference on Neural Information Processing Systems. 2016, 307–315
|
28 |
Y, Shen C Feng, Y Yang, D Tian. Mining point cloud local structures by kernel correlation and graph pooling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 4548–4557
https://doi.org/10.1109/CVPR.2018.00478
|
29 |
Y Yang, C Feng, Y Shen, D Tian. Foldingnet: point cloud auto-encoder via deep grid deformation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 206–215
https://doi.org/10.1109/CVPR.2018.00029
|
30 |
B Hua, M Tran, S Yeung. Pointwise convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 984–993
https://doi.org/10.1109/CVPR.2018.00109
|
31 |
H You, Y Feng, R Ji, Y Gao. PVNet: a joint convolutional network of point cloud and multi-view for 3D shape recognition. In: Proceedings of the 26th ACM International Conference on Multimedia. 2018, 1310–1318
https://doi.org/10.1145/3240508.3240702
|
32 |
M Jiang, Y Wu, C Lu. Pointsift: a sift-like network module for 3D point cloud semantic segmentation. 2018, arXiv preprint arXiv:1807.00652
https://doi.org/10.1109/IGARSS.2019.8900102
|
33 |
J Li, B Chen, G Lee. So-net: self-organizing network for point cloud analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 9397–9406
https://doi.org/10.1109/CVPR.2018.00979
|
34 |
Y Lecun, L Bottou, Y Bengio, P Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1998, 86(11): 2278–2324
https://doi.org/10.1109/5.726791
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|