Weakly-Supervised Point Cloud Semantic Segmentation with Consistency Constraint and Feature Enhancement

Dong Wei; Yifan Bai; He Sun; Jingtian Zhang

doi:10.3788/LOP241945

[1] Ai D, Zhang X Y, Xu C et al. Advancements in semantic segmentation methods for large-scale point clouds based on deep learning[J]. Laser & Optoelectronics Progress, 61, 1200003(2024).

[2] Wang J Y, Liu Y, Tan H L et al. A survey on weakly supervised 3D point cloud semantic segmentation[J]. IET Computer Vision, 18, 329-342(2024).

[3] Charles R Q, Hao S, Mo K C et al. PointNet: deep learning on point sets for 3D classification and segmentation[C], 77-85(2017).

[4] Charles R Q, Yi L, Hao S et al. PointNet++: deep hierarchical feature learning on point sets in a metric space[EB/OL]. https://arxiv.org/abs/1706.02413

[5] Zuo M, Liu Y Y, Cui H et al. Semantic segmentation method of point cloud based on sparse convolution and attention mechanism[J]. Laser & Optoelectronics Progress, 60, 2015002(2023).

[6] Zhang L J, Bi Y W, Liu Y W et al. Augmented edge graph convolutional networks for semantic segmentation of 3D point clouds[J]. Laser & Optoelectronics Progress, 61, 0837009(2024).

[7] Xu X, Lee G H. Weakly supervised semantic point cloud segmentation: towards 10× fewer labels[C], 13703-13712(2020).

[8] Zhang Y C, Qu Y Y, Xie Y et al. Perturbed self-distillation: weakly supervised large-scale point cloud semantic segmentation[C], 15500-15508(2021).

[9] Hu Q Y, Yang B, Fang G C et al. SQN: weakly-supervised semantic segmentation of large-scale 3D point clouds[M]. Computer vision-ECCV 2022, 13687, 600-619(2022).

[10] Lee M S, Yang S W, Han S W. GaIA: graphical information gain based attention network for weakly supervised point cloud semantic segmentation[C], 582-591(2023).

[11] Liu L Z, Zhuang Z W, Huang S X et al. CPCM: contextual point cloud modeling for weakly-supervised point cloud semantic segmentation[C], 18367-18376(2023).

[12] Wu Y S, Yan Z Z, Cai S C et al. PointMatch: a consistency training framework for weakly supervised semantic segmentation of 3D point clouds[J]. Computers & Graphics, 116, 427-436(2023).

[13] Wu Z H, Wu Y C, Lin G S et al. Reliability-adaptive consistency regularization for weakly-supervised point cloud segmentation[J]. International Journal of Computer Vision, 132, 2276-2289(2024).

[14] Zhang Y C, Li Z H, Xie Y et al. Weakly supervised semantic segmentation for large-scale point cloud[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 3421-3429(2021).

[15] Liu Z Z, Qi X J, Fu C W. One thing one click: a self-training approach for weakly supervised 3D semantic segmentation[C], 1726-1736(2021).

[16] Lan Y X, Zhang Y C, Qu Y Y et al. Weakly supervised 3D segmentation via receptive-driven pseudo label consistency and structural consistency[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 37, 1222-1230(2023).

[17] Tang L Y, Chen Z, Zhao S S et al. All points matter: entropy-regularized distribution alignment for weakly-supervised 3D segmentation[EB/OL]. https://export.arxiv.org/abs/2305.15832

[18] Xie S N, Gu J T, Guo D M et al. PointContrast: unsupervised pre-training for 3D point cloud understanding[M]. Computer vision-ECCV 2020, 12348, 574-591(2020).

[19] Li M T, Xie Y, Shen Y H et al. HybridCR: weakly-supervised 3D point cloud semantic segmentation via hybrid contrastive regularization[C], 14910-14919(2022).

[20] Yao B C, Xiao H, Zhuang J Y et al. Weakly supervised learning for point cloud semantic segmentation with dual teacher[J]. IEEE Robotics and Automation Letters, 8, 6347-6354(2023).

[21] Hu Q Y, Yang B, Xie L H et al. RandLA-net: efficient semantic segmentation of large-scale point clouds[C], 11105-11114(2020).

[22] Landrieu L, Simonovsky M. Large-scale point cloud semantic segmentation with superpoint graphs[C], 4558-4567(2018).

[23] Zhao H S, Jiang L, Fu C W et al. PointWeb: enhancing local neighborhood features for point cloud processing[C], 5560-5568(2019).

[24] Thomas H, Qi C R, Deschaud J E et al. KPConv: flexible and deformable convolution for point clouds[C], 6410-6419(2019).

[25] Wang Y, Sun Y B, Liu Z W et al. Dynamic graph CNN for learning on point clouds[J]. ACM Transactions on Graphics, 38, 146(2019).

微信扫一扫：分享

微信扫一扫：分享