- 中国精品科技期刊
- CCF推荐A类中文期刊
- 计算领域高质量科技期刊T1类
| Citation: |
Han Bing, Zhang Xinyun, Ren Shuang. Survey of Convolution Operations Based on 3D Point Clouds[J]. Journal of Computer Research and Development, 2023, 60(4): 873-902. DOI: 10.7544/issn1000-1239.202220135
|
With the popularity of three-dimensional (3D) scanning devices, like the depth cameras and LiDARs, using point clouds to represent 3D data becomes ubiquitous. Compared with two-dimensional (2D) images, point clouds can provide richer information and capture more 3D structures. Therefore, point cloud learning has recently attracted a surge of research interests in computer vision community and promoted various emerging applications, such as robotic manipulation, autonomous driving and augmented reality. Generally, the learned representations of point clouds should have the characteristics of permutation invariant, transformation invariant (e.g., rotation and translation) and shape distinguishability. Therefore, in recent years, more and more researchers have carried out research on using deep learning (DL) to deal with point clouds. Among them, the convolution operations in convolutional neural networks (CNNs) have the characteristics of weight sharing, local aggregation and transformation invariance, which can effectively reduce the complexity of the networks and the number of training parameters. Meanwhile, CNNs have been successfully used to solve various 2D vision problems of images and videos with strong robustness. Therefore, CNNs attract great attention of researchers and are introduced into some point cloud tasks. However, the traditional standard convolution operations cannot directly act on the irregular data such as point clouds. Therefore, some researchers carry out in-depth explorations on the convolution operations and then propose a variety of convolutional strategies and networks to improve the computational efficiency and algorithm performance. To stimulate future research, we first summarize convolutional methods used in existing point cloud research, including projection-based methods, voxel-based methods, lattice-based methods, graph-based methods and point-based methods. After that, we focus on the recent progress in convolution operators and networks based on point clouds mainly including discrete convolutions and continuous convolutions. In addition, the performances of networks using various point-based convolution operators in some related tasks (such as classification and segmentation) are comprehensively analyzed. Then we quantitatively compare these methods on some synthetic datasets and real-scanned datasets, and obtain relative state-of-the-art (SOTA) methods of each point cloud task. Extensive experiments can verify the performances as well as the effectiveness of these proposed methods. Finally, aiming at some existing problems and challenges, we also present insightful observations together with inspiring future research directions.
| [1] |
Kato S, Tokunaga S, Maruyama Y, et al. Autoware on board: Enabling autonomous vehicles with embedded systems[C] //Proc of the 9th IEEE Int Conf on Cyber-Physical Systems (ICCPS). Piscataway, NJ: IEEE, 2018: 287−296
|
| [2] |
Pomerleau F, Colas F, Siegwart R. A review of point cloud registration algorithms for mobile robotics[J]. Foundations and Trends in Robotics, 2015, 4(1): 1−104 doi: 10.1561/2300000035
|
| [3] |
Guo Yulan, Wang Hanyun, Hu Qingyong, et al. Deep learning for 3D point clouds: A survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(12): 4338−4364 doi: 10.1109/TPAMI.2020.3005434
|
| [4] |
Qi C R, Su Hao, Mo Kaichun, et al. PointNet: Deep learning on point sets for 3D classification and segmentation[C] //Proc of the 30th IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2017: 652 − 660
|
| [5] |
Qi C R, Yi Li, Su Hao, et al. PointNet++: Deep hierarchical feature learning on point sets in a metric space[C/OL] //Proc of the 31st Neural Information Processing Systems (NIPS). Cambridge, MA: MIT Press, 2017[2022-06-14]. https://proceedings.neurips.cc/paper/2017/file/d8bf84be3800d12f74d8b05e9b89836f-Paper.pdf
|
| [6] |
LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278−2324 doi: 10.1109/5.726791
|
| [7] |
Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C] //Proc of the 27th IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2014: 580−587
|
| [8] |
Hou Le, Samaras D, Kurc T M, et al. Patch-based convolutional neural network for whole slide tissue image classification[C] //Proc of the 29th IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2016: 2424−2433
|
| [9] |
Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation[C] //Proc of the 18th Int Conf on Medical Image Computing and Computer-Assisted Intervention (MICCAI). Berlin: Springer, 2015: 234−241
|
| [10] |
Chen L C, Papandreou G, Kokkinos I, et al. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834−848 doi: 10.1109/TPAMI.2017.2699184
|
| [11] |
Qi C R, Su Hao, Niebner M, et al. Volumetric and multi-view CNNs for object classification on 3D data[C] //Proc of the 29th IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2016: 5648−5656
|
| [12] |
Huang Haibin, Kalogerakis E, Chaudhuri S, et al. Learning local shape descriptors from part correspondences with multi-view convolutional networks[J]. ACM Transactions on Graphics, 2017, 37(1): 1−14
|
| [13] |
Wei Xin, Yu Ruixuan, Sun Jian. View-GCN: View-based graph convolutional network for 3D shape analysis[C] //Proc of the 33rd IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2020: 1847−1856
|
| [14] |
Xu Sheng, Zhou Xuan, Ye Weidu, et al. Classification of 3D point clouds by a new augmentation convolutional neural network[J/OL]. IEEE Geoscience and Remote Sensing Letters, 2022 [2022 − 06-01]. https://doi.org/10.1109/LGRS.2022.3141073
|
| [15] |
Tatarchenko M, Park J, Koltun V, et al. Tangent convolutions for dense prediction in 3D[C] //Proc of the 31st IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2018: 3887−3896
|
| [16] |
Komarichev A, Zhong Zichun, Hua Jing. A-CNN: Annularly convolutional neural networks on point clouds[C] //Proc of the 32nd IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2019: 7413−7422
|
| [17] |
Lin Yiqun, Yan Zizheng, Huang Haibin, et al. FPConv: Learning local flattening for point convolution[C] //Proc of the 33rd IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2020: 4292−4301
|
| [18] |
Maturana D, Scherer S. VoxNet: A 3D convolutional neural network for real-time object recognition[C] //Proc of the 28th IEEE Int Conf on Intelligent Robots and Systems (IROS). Piscataway, NJ: IEEE, 2015: 922−928
|
| [19] |
Zhou Yin, Tuzel O. VoxelNet: End-to-end learning for point cloud based 3D object detection[C] //Proc of the 31st IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2018: 4490−4499
|
| [20] |
Graham B, Engelcke M, Laurens V D M. 3D semantic segmentation with submanifold sparse convolutional networks[C] //Proc of the 31st IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2018: 9224−9232
|
| [21] |
Ben-Shabat Y, Lindenbaum M, Fischer A. 3DmFV: Three-dimensional point cloud classification in real-time using convolutional neural networks[J]. IEEE Robotics and Automation Letters, 2018, 3(4): 3145−3152 doi: 10.1109/LRA.2018.2850061
|
| [22] |
Liu Zhijian, Tang Haotian, Lin Yujun, et al. Point-voxel CNN for efficient 3D deep learning[C/OL] //Proc of the 33rd Neural Information Processing Systems (NeurIPS). Cambridge, MA: MIT Press, 2019 [2022-06-16]. https://proceedings.neurips.cc/paper/2019/file/5737034557ef5b8c02c0e46513b98f90-Paper.pdf
|
| [23] |
Meng H Y, Gao Lin, Lai Yukun, et al. VV-Net: Voxel VAE net with group convolutions for point cloud segmentation[C] //Proc of the 17th IEEE Int Conf on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2019: 8500−8508
|
| [24] |
Wang Zongji, Lu Feng. VoxSegNet: Volumetric CNNs for semantic part segmentation of 3D shapes[J]. IEEE Transactions on Visualization and Computer Graphics, 2020, 26(9): 2919−2930 doi: 10.1109/TVCG.2019.2896310
|
| [25] |
Su Hang, Jampani V, Sun Deqing, et al. SPLATNet: Sparse lattice networks for point cloud processing[C] //Proc of the 31st IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2018: 2530−2539
|
| [26] |
Rao Yongming, Lu Jiwen, Zhou Jie. Spherical fractal convolutional neural networks for point cloud recognition[C] //Proc of the 32nd IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2019: 452−460
|
| [27] |
Wang Chu, Samari B, Siddiqi K. Local spectral graph convolution for point set feature learning[C] //Proc of the 18th European Conf on Computer Vision (ECCV). Berlin: Springer, 2018: 56−71
|
| [28] |
Zhang Yingxue, Rabbat M. A graph-CNN for 3D point cloud classification[C] //Proc of the 43rd IEEE Int Conf on Acoustics, Speech, and Signal Processing (ICASSP). Piscataway, NJ: IEEE, 2018: 6279−6283
|
| [29] |
Te Gusi, Hu Wei, Zheng Amin, et al. RGCNN: Regularized graph CNN for point cloud segmentation[C] //Proc of the 26th ACM Int Conf on Multimedia (ACMMM). New York: ACM, 2018: 746−754
|
| [30] |
Li Ruoyu, Wang Sheng, Zhu Feiyun, et al. Adaptive graph convolutional neural networks[C] //Proc of the 32nd AAAI Conf on Artificial Intelligence (AAAI). Palo Alto, CA: AAAI, 2018: 3546−3553
|
| [31] |
Feng Yifan, You Haoxuan, Zhang Zizhao, et al. Hypergraph neural networks[C] //Proc of the 33rd AAAI Conf on Artificial Intelligence (AAAI). Palo Alto, CA: AAAI, 2019: 3558−3565
|
| [32] |
Simonovsky M, Komodakis N. Dynamic edge-conditioned filters in convolutional neural networks on graphs[C] //Proc of the 30th IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2017: 29−38
|
| [33] |
Dominguez M, Dhamdhere R, Petkar A, et al. General-purpose deep point cloud feature extractor[C] //Proc of the IEEE Winter Conf on Applications of Computer Vision (WACV). Piscataway, NJ: IEEE, 2018: 1972−1981
|
| [34] |
Shen Yiru, Feng Chen, Yang Yaoqing, et al. Mining point cloud local structures by kernel correlation and graph pooling[C] //Proc of the 31st IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2018: 4548−4557
|
| [35] |
Landrieu L, Simonovsky M. Large-scale point cloud semantic segmentation with superpoint graphs[C] //Proc of the 31st IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2018: 4558−4567
|
| [36] |
Landrieu L, Boussaha M. Point cloud over-segmentation with graph-structured deep metric learning[C] //Proc of the 32nd IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2019: 7432−7441
|
| [37] |
Wang Lei, Huang Yuchun, Hou Yaolin, et al. Graph attention convolution for point cloud semantic segmentation[C] //Proc of the 32nd IEEE Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2019: 10288−10297
|
| [38] |
Kang Zhiheng, Li Ning. PyramNet: Point cloud pyramid attention network and graph embedding module for classification and segmentation[C/OL] //Proc of the 32nd Int Conf on Neural Information Processing (ICONIP). Berlin: Springer, 2019 [2022-06-16]. http://ajiips.com.au/papers/V16.2/v16n2_39 − 47.pdf
|
| [39] |
Wang Yue, Sun Yongbin, Liu Ziwei, et al. Dynamic graph CNN for learning on point clouds[J]. ACM Transactions on Graphics, 2019, 38(5): 146:1−12
|
| [40] |
Ma Yanni, Guo Yulan, Liu Hao, et al. Global context reasoning for semantic segmentation of 3D point clouds[C] //Proc of the IEEE Winter Conf on Applications of Computer Vision (WACV). Piscataway, NJ: IEEE, 2020: 2920−2929
|
| [41] |
Xu Qiangeng, Sun Xudong, Wu Choying, et al. Grid-GCN for fast and scalable point cloud learning[C] //Proc of the 33rd IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2020: 5660−5669
|
| [42] |
Lei Huan, Akhtar N, Mian A. SegGCN: Efficient 3D point cloud segmentation with fuzzy spherical kernel[C] //Proc of the 33rd IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2020: 11608−11617
|
| [43] |
Lei Huan, Akhtar N, Mian A. Spherical kernel for efficient graph convolution on 3D point clouds[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(10): 3664−3680 doi: 10.1109/TPAMI.2020.2983410
|
| [44] |
Liu Weiping, Sun Jia, Li Wanyi, et al. Deep learning on point clouds and its application: A survey[J]. Sensors, 2019, 19(19): 1−22 doi: 10.1109/JSEN.2019.2925951
|
| [45] |
Bello S A, Yu Shangshu, Wang Cheng. Review: Deep learning on 3D point clouds[J]. Remote Sensing, 2020, 12(11): 1−34
|
| [46] |
Li Ying, Ma Lingfei, Zhong Zilong, et al. Deep learning for LiDAR point clouds in autonomous driving: A review[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(8): 3412−3432 doi: 10.1109/TNNLS.2020.3015992
|
| [47] |
李宝,程志全,党岗,等. 3D点云法向量估计综述[J]. 计算机工程与应用,2010,46(23):1−7
Li Bao, Cheng Zhiquan, Dang Gang, et al. Survey on normal estimation for 3D point clouds[J]. Computer Engineering and Applications, 2010, 46(23): 1−7 (in Chinese)
|
| [48] |
Nguyen A, Le B. 3D point cloud segmentation: A survey[C] //Proc of the 6th IEEE Conf on Robotics, Automation and Mechatronics (RAM). Piscataway, NJ: IEEE, 2013: 225−230
|
| [49] |
Zhang Jiaying, Zhao Xiaoli, Chen Zheng, et al. A review of deep learning-based semantic segmentation for point cloud[J]. IEEE Access, 2019, 7: 179118−179133 doi: 10.1109/ACCESS.2019.2958671
|
| [50] |
Xie Yuxing, Tian Jiaojiao, Zhu Xiaoxiang. Linking points with labels in 3D: A review of point cloud semantic segmentation[J]. IEEE Geoscience and Remote Sensing Magazine, 2020, 8(4): 38−59 doi: 10.1109/MGRS.2019.2937630
|
| [51] |
景庄伟,管海燕,臧玉府,等. 基于深度学习的点云语义分割研究综述[J]. 计算机科学与探索,2021,5(1):1−26 doi: 10.3778/j.issn.1673-9418.2006025
Jing Zhuangwei, Guan Haiyan, Zang Yufu, et al. Survey of point cloud semantic segmentation based on deep learning[J]. Journal of Frontiers of Computer Science and Technology, 2021, 5(1): 1−26 (in Chinese) doi: 10.3778/j.issn.1673-9418.2006025
|
| [52] |
Huang Xiaoshui, Mei Guofeng, Zhang Jian, et al. A comprehensive survey on point cloud registration[J]. arXiv preprint, arXiv: 2103.02690, 2021
|
| [53] |
Wang Haowen, Li Zirui, Gong Jianwei. Sequential point cloud prediction in interactive scenarios: A survey[C] //Proc of the 9th China Automation Congress (CAC). Piscataway, NJ: IEEE, 2021: 3862−3867
|
| [54] |
马帅,刘建伟,左信. 图神经网络综述[J]. 计算机研究与发展,2022,59(1):47−80
Ma Shuai, Liu Jianwei, Zuo Xin. Survey on graph neural network[J]. Journal of Computer Research and Development, 2022, 59(1): 47−80 (in Chinese)
|
| [55] |
Hua B S, Tran M K, Yeung S K. Pointwise convolutional neural networks[C] //Proc of the 31st IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2018: 984−993
|
| [56] |
Li Yangyan, Bu Rui, Sun Mingchao, et al. PointCNN: Convolution on χ-Transformed points[C/OL] //Proc of the 32nd Neural Information Processing Systems (NeurIPS). Cambridge, MA: MIT Press, 2018 [2022-06-16]. https://proceedings.neurips.cc/paper/2018/file/f5f8590cd58a54e94377e6ae2eded4d9-Paper.pdf
|
| [57] |
Zhang Hua, Ren Kai, Zheng Nanshan, et al. A multiscale convolutional neural network with color vegetation indices for semantic labeling of point cloud[J/OL]. IEEE Geoscience and Remote Sensing Letters, 2022[2022-06-01]. https://doi.org/10.1109/LGRS.2021.3079242
|
| [58] |
Lan Shiyi, Yu Ruichi, Yu Gang, et al. Modeling local geometric structure of 3D point clouds using Geo-CNN[C] //Proc of the 32nd IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2019: 998−1008
|
| [59] |
Gong Jingyu, Xu Jiachen, Tan Xin, et al. Boundary-aware geometric encoding for semantic segmentation of point clouds[C] //Proc of the 35th AAAI Conf on Artificial Intelligence (AAAI). Palo Alto, CA: AAAI, 2021: 1424−1432
|
| [60] |
Zhang Zhiyuan, Hua B S, Yeung S K. ShellNet: Efficient point cloud convolutional neural networks using concentric shells statistics[C] //Proc of the 17th IEEE Int Conf on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2019: 1607−1616
|
| [61] |
Lei Huan, Akhtar N, Mian A. Octree guided CNN with spherical kernels for 3D point clouds[C] //Proc of the 32nd IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2019: 9623−9632
|
| [62] |
Wang Pengshuai, Liu Yang, Guo Yuxiao, et al. O-CNN: Octree-based convolutional neural networks for 3D shape analysis[J]. ACM Transactions on Graphics, 2017, 36(4): 72:1−11
|
| [63] |
Pan Liang, Wang Pengfei, Chew C M. PointAtrousNet: Point atrous convolution for point cloud analysis[J]. IEEE Robotics and Automation Letters, 2019, 4(4): 4035−4041 doi: 10.1109/LRA.2019.2927948
|
| [64] |
Engelmann F, Kontogianni T, Leibe B. Dilated point convolutions: On the receptive field size of point convolutions on 3D point clouds[C] //Proc of the 37th IEEE Int Conf on Robotics and Automation (ICRA). Piscataway, NJ: IEEE, 2020: 9463−9469
|
| [65] |
Cui Yunhao, An Yi, Sun Wei, et al. Lightweight attention module for deep learning on classification and segmentation of 3D point clouds[J/OL]. IEEE Transactions on Instrumentation and Measurement, 2021[2022-06-01]. https://doi.org/10.1109/TIM.2020.3013081
|
| [66] |
Chen Haiwei, Liu Shichen, Chen Weikai, et al. Equivariant point network for 3D point cloud analysis[C] //Proc of the 34th IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2021: 14514−14523
|
| [67] |
Dang Jisheng, Yang Jun. HIGCNN: Hierarchical interleaved group convolutional neural networks for point clouds analysis[C] //Proc of the 46th IEEE Int Conf on Acoustics, Speech, and Signal Processing (ICASSP). Piscataway, NJ: IEEE, 2021: 2825−2829
|
| [68] |
Mao Jiageng, Wang Xiaogang, Li Hongsheng. Interpolated convolutional networks for 3D point cloud understanding[C] //Proc of the 17th IEEE Int Conf on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2019: 1578−1587
|
| [69] |
Nguyen A D, Choi S, Kim W, et al. Statistical convolution on unordered point set[C] //Proc of the 27th IEEE Int Conf on Image Processing (ICIP). Piscataway, NJ: IEEE, 2020: 3468−3472
|
| [70] |
Thomas H, Qi C R, Deschaud J E, et al. KPConv: Flexible and deformable convolution for point clouds[C] //Proc of the 17th IEEE Int Conf on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2019: 6410−6419
|
| [71] |
Yan Kunping, Hu Qingyong, Wang Hanyun, et al. Continuous mapping convolution for large-scale point clouds semantic segmentation[J/OL]. IEEE Geoscience and Remote Sensing Letters, 2021, 19 [2022-06-01]. https://doi.org/10.1109/LGRS.2021.3107006
|
| [72] |
Zhang Zhiyuan, Hua B S, Chen Wei, et al. Global context aware convolutions for 3D point cloud understanding[C] //Proc of the 8th Int Conf on 3D Vision (3DV). Piscataway, NJ: IEEE, 2020: 210−219
|
| [73] |
Yang Yirong, Fan Bin, Liu Yongcheng, et al. Deep space probing for point cloud analysis[C] //Proc of the 25th Int Conf on Pattern Recognition (ICPR). Piscataway, NJ: IEEE, 2021: 10235−10242
|
| [74] |
Xu Mutian, Ding Runyu, Zhao Hengshuang, et al. PAConv: Position adaptive convolution with dynamic kernel assembling on point clouds[C] //Proc of the 34th IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2021: 3173−3182
|
| [75] |
Groh F, Wieschollek P, Lensch H P A. Flex-Convolution (deep learning beyond grid-worlds)[C] //Proc of the 13th Asian Conf on Computer Vision (ACCV). Berlin: Springer, 2018: 105−122
|
| [76] |
Boulch A. ConvPoint: Continuous convolutions for point cloud processing[J]. Computers and Graphics, 2020, 88: 24−34 doi: 10.1016/j.cag.2020.02.005
|
| [77] |
Klokov R, Lempitsky V. Escape from cells: Deep kd-networks for the recognition of 3D point cloud models[C] //Proc of the 16th IEEE Int Conf on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2017: 863−872
|
| [78] |
Wang Shenlong, Suo Simon, Ma W C, et al. Deep parametric continuous convolutional neural networks[C] //Proc of the 31st IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2018: 2589−2597
|
| [79] |
Xu Yifan, Fan Tianqi, Xu Mingye, et al. SpiderCNN: Deep learning on point sets with parameterized convolutional filters[C] //Proc of the 16th European Conf on Computer Vision (ECCV). Berlin: Springer, 2018: 90−105
|
| [80] |
Hermosilla P, Ritschel T, Vázquez P P, et al. Monte Carlo convolution for learning on nonuniformly sampled point clouds[J]. ACM Transactions on Graphics, 2018, 37(6): 235:1−12
|
| [81] |
Wu Wenxuan, Qi Zhongang, Li Fuxin. PointConv: Deep convolutional networks on 3D point clouds[C] //Proc of the 32nd IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2019: 9613−9622
|
| [82] |
Wang Fei, Zhang Xing, Jiang Yong, et al. PatchCNN: An explicit convolution operator for point clouds perception[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 18(4): 726−730 doi: 10.1109/LGRS.2020.2981507
|
| [83] |
Liu Yongcheng, Fan Bin, Xiang Shiming, et al. Relation-shape convolutional neural network for point cloud analysis[C] //Proc of the 32nd IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2019: 8887−8896
|
| [84] |
Liu Yongcheng, Fan Bin, Meng Gaofeng, et al. DensePoint: Learning densely contextual representation for efficient point cloud processing[C] //Proc of the 17th IEEE Int Conf on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2019: 5238−5247
|
| [85] |
Atzmon M, Haggai M, Lipman Y. Point convolutional neural networks by extension operators[J]. ACM Transactions on Graphics, 2018, 37(4): 71:1−12
|
| [86] |
Poulenard A, Rakotosaona M J, Ponty Y, et al. Effective rotation-invariant point CNN with spherical harmonics kernels[C] //Proc of the 7th Int Conf on 3D Vision (3DV). Piscataway, NJ: IEEE, 2019: 47−56
|
| [87] |
Zhang Zhiyuan, Hua B S, Rosen D W, et al. Rotation invariant convolutions for 3D point clouds deep learning[C] //Proc of the 7th Int Conf on 3D Vision (3DV). Piscataway, NJ: IEEE, 2019: 204−213
|
| [88] |
Thomas H. Rotation-invariant point convolution with multiple equivariant alignments[C] //Proc of the 8th Int Conf on 3D Vision (3DV). Piscataway, NJ: IEEE, 2020: 504−513
|
| [89] |
Wu Zhirong, Song Shuran, Khosla A, et al. 3D ShapeNets: A deep representation for volumetric shapes[C] //Proc of the 28th IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2015: 1912−1920
|
| [90] |
Chang A X, Funkhouser T, Guibas L, et al. ShapeNet: An information-rich 3D model repository[J]. arXiv preprint, arXiv: 1512.03012, 2015
|
| [91] |
Armeni I, Sener O, Zamir A R, et al. 3D semantic parsing of large-scale indoor spaces[C] //Proc of the 29th IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2016: 1534−1543
|
| [92] |
Dai A, Chang A X, Savva M, et al. ScanNet: Richly-annotated 3D reconstructions of indoor scenes[C] //Proc of the 30th IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2017: 2432−2443
|
| [93] |
Hackel T, Savinov N, Ladicky L, et al. SEMANTIC3D. NET: A new large-scale point cloud classification benchmark[J]. Journal of Photogrammetry and Remote Sensing, 2017, IV-1/W1: 91−98
|
| [94] |
Behley J, Garbade M, Milioto A, et al. SemanticKITTI: A dataset for semantic scene understanding of LiDAR sequences[C] //Proc of the 17th IEEE Int Conf on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2019: 9296−9306
|
| [95] |
Rodriguez D, Huber F, Behnke S. Category-level 3D non-rigid registration from single-view RGB images[C] //Proc of the 33rd IEEE Int Conf on Intelligent Robots and Systems (IROS). Piscataway, NJ: IEEE, 2020: 10617−10624
|
| [96] |
Geiger A, Lenz P, Urtasun R. Are we ready for autonomous driving? The KITTI vision benchmark suite[C] //Proc of the 25th IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2012: 3354−3361
|
| [97] |
Fei Ben, Yang Weidong, Chen Wenming, et al. Comprehensive review of deep learning-based 3D point clouds completion processing and analysis[J]. arXiv preprint, arXiv: 2203.03311, 2022
|
| [98] |
Zhang Yan, Zhao Wenhan, Sun Bo, et al. Point cloud upsampling algorithm: A systematic review[J]. Algorithms, 2022, 15(124): 1−17
|
| [99] |
Pistilli F, Fracastoro G, Valsesia D, et al. Learning robust graph-convolutional representations for point cloud denoising[J]. IEEE Journal of Selected Topics in Signal Processing, 2021, 15(2): 402−414 doi: 10.1109/JSTSP.2020.3047471
|
| [100] |
Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C/OL] //Proc of the 31st Neural Information Processing Systems (NIPS). Cambridge, MA: MIT Press, 2017 [2022-06-16]. https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
|
| [101] |
Han Kai, Wang Yunhe, Chen Hanting, et al. A survey on vision transformer[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(1): 87−110 doi: 10.1109/TPAMI.2022.3152247
|
| [102] |
Cordonnier J B, Loukas A, Jaggi M. On the relationship between self-attention and convolutional layers[J]. arXiv preprint, arXiv: 1911.03584, 2020
|
| [103] |
Dong Yihe, Cordonnier J B, Loukas A. Attention is not all you need: Pure attention loses rank doubly exponentially with depth[J]. arXiv preprint, arXiv: 2103.03404, 2021
|
| [104] |
Srinivas A, Lin T Y, Parmar N, et al. Bottleneck transformers for visual recognition[C] //Proc of the 34th IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2021: 16519−16529
|
| [105] |
Touvron H, Cord M, Douze M, et al. Training data-efficient image transformers & distillation through attention[J]. arXiv preprint, arXiv: 2012.12877, 2021
|
| [106] |
Stéphane d'A, Touvron H, Leavitt M, et al. ConViT: Improving vision transformers with soft convolutional inductive biases[J]. arXiv preprint, arXiv: 2103.10697, 2021
|
| [107] |
Yuan Kun, Guo Shaopeng, Liu Ziwei, et al. Incorporating convolution designs into visual transformers[C] //Proc of the 18th IEEE Int Conf on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2021: 579−588
|
| [108] |
Zhao Hengshuang, Jiang Li, Jia Jiaya, et al. Point transformer[C] //Proc of the 18th IEEE Int Conf on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2021: 16259−16268
|
| [1] | Li Maowen, Qu Guoyuan, Wei Dazhou, Jia Haipeng. Performance Optimization of Neural Network Convolution Based on GPU Platform[J]. Journal of Computer Research and Development, 2022, 59(6): 1181-1191. DOI: 10.7544/issn1000-1239.20200985 |
| [2] | Wang Lei, Xiong Yuning, Li Yunpeng, Liu Yuanyuan. A Collaborative Recommendation Model Based on Enhanced Graph Convolutional Neural Network[J]. Journal of Computer Research and Development, 2021, 58(9): 1987-1996. DOI: 10.7544/issn1000-1239.2021.20200617 |
| [3] | Liu Yanxiao, Wu Ping, Sun Qindong. Secret Image Sharing Schemes Based on Region Convolution Neural Network[J]. Journal of Computer Research and Development, 2021, 58(5): 1065-1074. DOI: 10.7544/issn1000-1239.2021.20200898 |
| [4] | Li Teng, Qiao Wei, Zhang Jiawei, Gao Yiyang, Wang Shenao, Shen Yulong, Ma Jianfeng. Privacy-Preserving Network Attack Provenance Based on Graph Convolutional Neural Network[J]. Journal of Computer Research and Development, 2021, 58(5): 1006-1020. DOI: 10.7544/issn1000-1239.2021.20200942 |
| [5] | Xing Xinying, Ji Junzhong, Yao Yao. Brain Networks Classification Based on an Adaptive Multi-Task Convolutional Neural Networks[J]. Journal of Computer Research and Development, 2020, 57(7): 1449-1459. DOI: 10.7544/issn1000-1239.2020.20190186 |
| [6] | Zhong Zhiquan, Yuan Jin, Tang Xiaoying. Left-vs-Right Eye Discrimination Based on Convolutional Neural Network[J]. Journal of Computer Research and Development, 2018, 55(8): 1667-1673. DOI: 10.7544/issn1000-1239.2018.20180215 |
| [7] | Hu Fei, You Zhiqiang, Liu Peng, Kuang Jishun. Circuit Design of Convolutional Neural Network Based on Memristor Crossbar Arrays[J]. Journal of Computer Research and Development, 2018, 55(5): 1097-1107. DOI: 10.7544/issn1000-1239.2018.20170107 |
| [8] | Du Yumeng, Zhang Weinan, Liu Ting. Topic Augmented Convolutional Neural Network for User Interest Recognition[J]. Journal of Computer Research and Development, 2018, 55(1): 188-197. DOI: 10.7544/issn1000-1239.2018.20160892 |
| [9] | Wang Peiqi, Gao Yuan, Liu Zhenyu, Wang Haixia, Wang Dongsheng. A Comparison Among Different Numeric Representations in Deep Convolution Neural Networks[J]. Journal of Computer Research and Development, 2017, 54(6): 1348-1356. DOI: 10.7544/issn1000-1239.2017.20170098 |
| [10] | Lü Guohao, Luo Siwei, Huang Yaping, Jiang Xinlan. A Novel Regularization Method Based on Convolution Neural Network[J]. Journal of Computer Research and Development, 2014, 51(9): 1891-1900. DOI: 10.7544/issn1000-1239.2014.20140266 |
| 1. |
王瑜，刘婉柔，解滨，韩力文. 斯特林曲线的离散卷积生成及其求值算法. 浙江大学学报(理学版). 2025(01): 122-132 .
| |
| 2. |
鲁子明，黄世秀，季铮，张思仪，黄翔翔. 基于PointNet优化网络的铁路站台语义分割. 现代电子技术. 2024(03): 68-72 .
| |
| 3. |
李越豪，王邓江，鉴海防，王洪昌，程清华. 基于BEV占位预测的激光-毫米波雷达融合目标检测算法. 计算机科学. 2024(06): 215-222 .
|
微信订阅号
（实时资讯）
微信服务号
（同步网站）
微信视频号
（视频分享）
CCF
（扫码入会）
Copyright © Editorial Department of Computer Research and Development
Supported by: Beijing Renhe Information Technology Co.,
Ltd. 
DownLoad: