Page 211 - 《软件学报》2025年第5期

程浩喆 等: 基于双向拟合掩码重建的多模态自监督点云表示学习 2111

[3] Qi Charles R, Su H, Mo KC, Guibas LJ. PointNet: Deep learning on point sets for 3D classification and segmentation. In: Proc. of the
2017 IEEE Conf. on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017. 652–660. [doi: 10.1109/CVPR.2017.16]
[4] Qi CR, Yi L, Su H, Guibas LJ. PointNet++: Deep hierarchical feature learning on point sets in a metric space. In: Proc. of the 31st Int’l
Conf. on Neural Information Processing Systems. Long Beach: Curran Associates Inc., 2017. 5105–5114.
[5] Wang Y, Sun YB, Liu ZW, Sarma SE, Bronstein MM, Solomon JM. Dynamic graph CNN for learning on point clouds. ACM Trans. on
Graphics, 2019, 38(5): 146. [doi: 10.1145/3326362]
[6] Cheng HZ, Lu J, Luo MX, Liu W, Zhang KB. PTANet: Triple attention network for point cloud semantic segmentation. Engineering
Applications of Artificial Intelligence, 2021, 102: 104239. [doi: 10.1016/j.engappai.2021.104239]
[7] Cheng HZ, Zhu JH, Lu J, Han X. EDGCNet: Joint dynamic hyperbolic graph convolution and dual squeeze-and-attention for 3D point
cloud segmentation. Expert Systems with Applications, 2024, 237: 121551. [doi: 10.1016/j.eswa.2023.121551]
[8] Lu J, Cheng HZ, Luo MX, Liu T, Zhang KB. PUConv: Upsampling convolutional network for point cloud semantic segmentation.
Electronics Letters, 2020, 56(9): 435–438. [doi: 10.1049/el.2019.3705]
[9] Sauder J, Sievers B. Self-supervised deep learning on point clouds by reconstructing space. In: Proc. of the 33rd Int’l Conf. on Neural
Information Processing Systems. Vancouver: Curran Associates Inc., 2019. 1161.
[10] Wang HC, Liu Q, Yue XY, Lasenby J, Kusner MJ. Unsupervised point cloud pre-training via occlusion completion. In: Proc. of the 2021
IEEE/CVF Int’l Conf. on Computer Vision. Montreal: IEEE, 2021. 9782–9792. [doi: 10.1109/ICCV48922.2021.00964]
[11] Xie SN, Gu JT, Guo DM, Qi CR, Guibas L, Litany O. PointContrast: Unsupervised pre-training for 3D point cloud understanding. In:
Proc. of the 16th European Conf. on Computer Vision. Glasgow: Springer, 2020. 574–591. [doi: 10.1007/978-3-030-58580-8_34]
[12] Shi PC, Cheng HZ, Han X, Zhou YY, Zhu JH. DualGenerator: Information interaction-based generative network for point cloud
completion. IEEE Robotics and Automation Letters, 2023, 8(10): 6627–6634. [doi: 10.1109/LRA.2023.3310406]
[13] Afham M, Dissanayake I, Dissanayake D, Dharmasiri A, Thilakarathna K, Rodrigo R. CrossPoint: Self-supervised cross-modal
contrastive learning for 3D point cloud understanding. In: Proc. of the 2022 IEEE/CVF Conf. on Computer Vision and Pattern
Recognition. New Orleans: IEEE, 2022. 9902–9912. [doi: 10.1109/CVPR52688.2022.00967]
[14] Wu ZR, Song SR, Khosla A, Yu F, Zhang LG, Tang XO, Xiao JX. 3D ShapeNets: A deep representation for volumetric shapes. In: Proc.
of the 2015 IEEE Conf. on Computer Vision and Pattern Recognition. Boston: IEEE, 2015. 1912–1920. [doi: 10.1109/CVPR.2015.
7298801]
[15] Uy MA, Pham QH, Hua BS, Nguyen T, Yeung SK. Revisiting point cloud classification: A new benchmark dataset and classification
model on real-world data. In: Proc. of the 2019 IEEE/CVF Int’l Conf. on Computer Vision. Seoul: IEEE, 2019. 1588–1597. [doi: 10.1109/
ICCV.2019.00167]
[16] Chang AX, Funkhouser T, Guibas L, Hanrahan P, Huang QX, Li ZM, Savarese S, Savva M, Song SR, Su H, Xiao JX, Yi L, Yu F.
ShapeNet: An information-rich 3D model repository. arXiv:1512.03012, 2015.
[17] Yu XM, Tang LL, Rao YM, Huang TJ, Zhou J, Lu JW. Point-BERT: Pre-training 3D point cloud Transformers with masked point
modeling. In: Proc. of the 2022 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022. 19313–19322.
[doi: 10.1109/CVPR52688.2022.01871]
[18] Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I. Attention is all you need. In: Proc. of the
31st Int’l Conf. on Neural Information Processing Systems. Long Beach: Curran Associates Inc., 2017. 6000–6010.
[19] Pang YT, Wang WX, Tay FEH, Liu W, Tian YH, Yuan L. Masked autoencoders for point cloud self-supervised learning. In: Proc. of the
17th European Conf. on Computer Vision. Tel Aviv: Springer, 2022. 604–621. [doi: 10.1007/978-3-031-20086-1_35]
[20] Zhang RR, Guo ZY, Fang RY, Zhao B, Wang D, Qiao Y, Li HS, Gao P. Point-M2AE: Multi-scale masked autoencoders for hierarchical
point cloud pre-training. In: Proc. of the 36th Int’l Conf. on Neural Information Processing Systems. New Orleans: Curran Associates
Inc., 2022. 1962.
[21] Liu HT, Cai M, Lee YJ. Masked discrimination for self-supervised learning on point clouds. In: Proc. of the 17th European Conf. on
Computer Vision. Tel Aviv: Springer, 2022. 657–675. [doi: 10.1007/978-3-031-20086-1_38]
[22] Zhang ZW, Girdhar R, Joulin A, Misra I. Self-supervised pretraining of 3D features on any point-cloud. In: Proc. of the 2021 IEEE/CVF
Int’l Conf. on Computer Vision. Montreal: IEEE, 2021. 10252–10263. [doi: 10.1109/ICCV48922.2021.01009]
[23] Wang D, Yang ZX. Self-supervised point cloud understanding via mask Transformer and contrastive learning. IEEE Robotics and
Automation Letters, 2023, 8(1): 184–191. [doi: 10.1109/LRA.2022.3224370]
[24] Mei GF, Huang XS, Liu J, Zhang J, Wu Q. Unsupervised point cloud pre-training via contrasting and clustering. In: Proc. of the 2022
IEEE Int’l Conf. on Image Processing. Bordeaux: IEEE, 2022. 66–70. [doi: 10.1109/ICIP46576.2022.9897388]
[25] Chen XL, He KM. Exploring simple siamese representation learning. In: Proc. of the 2021 IEEE/CVF Conf. on Computer Vision and
Pattern Recognition. Nashville: IEEE, 2021. 15750–15758. [doi: 10.1109/CVPR46437.2021.01549]
[26] Chen YJ, Nießner M, Dai A. 4DContrast: Contrastive learning with dynamic correspondences for 3D scene understanding. In: Proc. of