浏览全部资源
扫码关注微信
Published Online： 23 December 2024 ，
移动端阅览
仇志江,张林,姚垚等.三维点云场景语义分割研究进展[J].中国图象图形学报,
Qiu Zhijiang,Zhang Lin,Yao Yao,et al.A survey on semantic segmentation in 3D point cloud scenes[J].Journal of Image and Graphics,
随着深度传感器技术的迅速发展和激光扫描仪的广泛应用，三维点云数据在自动驾驶、机器人技术、地理信息系统、制造业等多个领域发挥着关键作用。本文从多个视角出发，对点云场景分割技术进行了详尽的综述。首先，文章介绍了本领域的常用数据集、采样方法及点云特征提取技术；接着，系统性地概述了点云场景的语义分割研究方法，涵盖基于点的方法（分为基于MLP（multilayer perceptron）的方法、基于Transformer的方法、基于图卷积的方法和其他方法）、基于体素的方法、基于视图的方法以及基于多模态融合方法；之后，对上述各种方法的研究成果进行了汇总与比较；最后，指出了当前面临的主要挑战，并探讨了未来可能的研究方向。
With the continuous advancement of depth sensing technology， particularly the widespread application of laser scanners （LiDAR） across diverse scenarios， 3D point cloud technology is playing a pivotal role in an increasing number of fields. These fields include， but are not limited to， autonomous driving， robotics， geographic information systems （GIS）， manufacturing， building information modeling （BIM）， cultural heritage preservation， virtual reality （VR） and augmented reality （AR）. As a high-precision， dense and detailed form of spatial data representation， 3D point clouds can accurately capture various types of information， including geometric shape， spatial structure， surface texture and environmental layout of objects. Consequently， the processing， analysis and comprehension of point cloud data are particularly significant in these applications， especially point cloud segmentation technology， which serves as the foundation for advanced tasks such as object recognition， scene understanding， map construction and dynamic environment monitoring. This paper aims to conduct a comprehensive review and in-depth exploration of current mainstream 3D point cloud segmentation methods from multiple perspectives， dissecting the latest advancements in this research domain. Specifically， it begins with a detailed analysis and discussion of the fundamentals of 3D point cloud segmentation， covering aspects such as datasets， performance evaluation metrics， sampling methods and feature extraction techniques. This paper summarizes currently publicly available mainstream point cloud datasets， including ShapeNet， Semantic3D， S3DIS and ScanNet， meticulously dissecting the characteristics， annotation forms， application scenarios and technical challenges associated with each dataset. Additionally， it delves into commonly utilized performance evaluation metrics in the semantic segmentation of point cloud scenes， including Overall Accuracy （OA）， Mean Class Accuracy （mAcc） and Mean Intersection over Union （mIoU）. These metrics provide effective means for quantifying and comparing model performance， facilitating comprehensive evaluations and improvements across different tasks and scenarios.In the data pre-processing phase， this paper systematically summarizes prevalent point cloud sampling strategies. Given that 3D point cloud data typically possess large scales and irregular distributions， a suitable sampling method is vital for reducing computational costs and enhancing model training efficiency. This paper introduces strategies such as Farthest Point Sampling （FPS）， Random Sampling and Grid Sampling， analyzing their application scenarios， advantages， disadvantages and specific implementation methods in various tasks. Furthermore， it discusses feature extraction techniques for 3D point clouds， encompassing various methods， including global feature extraction， local feature extraction and the fusion of global and local features. Through effective feature extraction， more discriminative representations can be provided for subsequent segmentation tasks， thereby aiding the model in improved object recognition and scene understanding.Building on this foundation， this paper systematically reviews 3D point cloud segmentation methods from four distinct perspectives： point-based methods， voxel-based methods， view-based methods and multi-modal fusion methods. Firstly， point-based methods directly process each point within the point cloud， maintaining the high resolution and density of the data while avoiding information loss. Point-based methods are further subdivided into MLP-based methods， Transformer-based models， GCN-based methods and other related approaches. Each category exhibits unique advantages in different application scenarios. For instance， MLP is effective at capturing local features of point clouds， while Transformer-based models excel in handling long-range dependencies and global relationships. Despite the strong performance of point-based methods， their direct processing of a large number of 3D points results in high computational complexity and relatively low efficiency when managing large-scale point cloud scenes.Secondly， this paper presents voxel-based methods， which process point cloud data by partitioning it into regular 3D grids （voxels）， effectively reducing data size and simplifying subsequent computations. This approach structures point cloud data， providing relatively stable performance in large-scale scenes， particularly applicable in scenarios with large scene sizes but lower resolution requirements. However， the inevitable information loss and reduction in spatial resolution during voxelization limit performance in handling fine-grained tasks.Next， the view-based approach processes the 3D point cloud by projecting it onto a 2D plane， leveraging mature 2D image processing techniques and convolutional neural networks （CNNs）. This method transforms the point cloud segmentation task into a traditional image segmentation problem， thereby enhancing processing efficiency， especially in scenarios where the point cloud density is high and rapid processing is required. However， projecting 3D information into 2D space may lead to the loss of spatial geometric information， resulting in potentially lower accuracy compared to methods that directly handle 3D point clouds in certain applications.Lastly， this paper explores multi-modal fusion methods， which combine various forms of data， such as point clouds， voxels and views， fully exploiting the complementarity of different modalities in scene understanding to enhance the accuracy， robustness and generalization ability of point cloud segmentation.Subsequently， this paper conducts a detailed analysis and comparison of the experimental results from different methods. Based on various datasets and performance evaluation metrics， it reveals the strengths and weaknesses of each method in diverse application scenarios. For example， point-based methods excel in fine segmentation tasks and can capture subtle geometric information， whereas voxel-based and view-based methods offer higher processing efficiency when dealing with large-scale point cloud scenes. Through comparative analysis of experimental results， this paper provides valuable references for point cloud segmentation tasks across different application scenarios.Finally， this paper summarizes the main challenges currently faced in the field of 3D point cloud segmentation， including the sparsity and irregularity of point cloud data， the influence of noise and missing points， insufficient generalization ability across diverse scenes and the demand for real-time processing. This paper also anticipates future research directions and proposes measures such as a deeper understanding of the complex semantic structures of point cloud data through the integration of large language models （LLMs）， the introduction of semi-supervised and unsupervised learning methods to reduce reliance on labeled data and enhancements in real-time performance and computational efficiency to further advance point cloud segmentation technology. It is hoped that this comprehensive review can provide a systematic reference for researchers and industrial applications in the field of point cloud technology， facilitating the implementation and development of 3D point cloud technology in a broader range of practical applications.
三维点云点云场景语义分割深度学习采样方法特征提取
3D point cloudpoint cloud scene semantic segmentationdeep learningsampling methodfeature extraction
Adam J M， Liu W， Zang Y， Afzal M， Bello S， Muhammad A， Wang C， Li J. 2023. Deep Learning-based semantic segmentation of urban-scale 3D meshes in remote sensing： A Survey. International Journal of Applied Earth Observation and Geoinformation. 121： 103365. ［DOI：10.1016/j.jag.2023.103365http://dx.doi.org/10.1016/j.jag.2023.103365］
Armeni I， Sener O， Zamir A R， Jiang H， Brilakis L， Fischer M and Savarese S. 2016. 3D Semantic parsing of large-scale indoor spaces//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas， NV， USA： IEEE： 1534-1543 ［DOI：10.1109/CVPR.2016.170http://dx.doi.org/10.1109/CVPR.2016.170］
Behley J， Garbade M， Milioto A， Quenzel J， Behnke S， Stachniss C and Gall J. 2019. SemanticKITTI： a dataset for semantic scene understanding of LiDAR sequences//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. Seoul， Korea （South）： IEEE： 9297-9307 ［DOI： 10. 1109 / ICCV. 2019. 00939http://dx.doi.org/10.1109/ICCV.2019.00939］
Chang A X， Funkhouser T， Guibas L， Hanrahan P and Huang Q. 2015. ShapeNet： an information-rich 3D model repository ［EB/OL］. ［2024-09-13］. http://arxiv.org/pdf/1512.03012.pdfhttp://arxiv.org/pdf/1512.03012.pdf
Chen B， Xie X and Liu S. 2023. A hybrid attention point cloud feature learning network based on dynamic graph convolution. Computer Technology and Development， 33（10）： 157-162
陈奔， 谢晓尧，刘嵩. 2023. 基于动态图卷积的混合注意力点云特征学习网络. 计算机技术与发展， 33（10）： 157-162 ［DOI：10.3969/j.issn.1673-629X.2023.10.024http://dx.doi.org/10.3969/j.issn.1673-629X.2023.10.024］
Dai A， Chang A X， Savva M， Halber M， Funkhouser T and Nießner M. 2017. ScanNet： richly-annotated 3D reconstructions of indoor scenes//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu， HI， USA：IEEE：5828-5839 ［DOI： 10.1109/CVPR.2017.261http://dx.doi.org/10.1109/CVPR.2017.261］
Du J and Cai G R. 2021. Point cloud semantic segmentation method based on multi-feature fusion and residual optimization. Journal of Image and Graphics，26（05）：1105-1116
杜静，蔡国榕. 2021. 多特征融合与残差优化的点云语义分割方法. 中国图象图形学报，26（05）：1105- 1116 ［DOI：10. 11834 / jig. 200374http://dx.doi.org/10.11834/jig.200374］
Guo M H， Cai J X， Liu Z N， Mu T J， Martin R R and Hu S M. 2021. PCT： point cloud transformer. Computational Visual Media， 7（2）： 187-199 ［DOI： 10. 1007 / s41095-021-0229-5http://dx.doi.org/10.1007/s41095-021-0229-5］
Hong Y， Zhen H， Chen P， Zheng S and Du Y. 2023. 3D-LLM： injecting the 3D world into large language models. Oh A， Naumann T， Globerson A//Advances in Neural Information Processing Systems. Curran Associates， Inc.： 20482-20494 ［DOI：10.48550/arxiv.2307.12981http://dx.doi.org/10.48550/arxiv.2307.12981］
Hu Q Y， Yang B， Xie L H， Rosa S， Guo Y L， Wang Z H， Trigoni N and Markham A. 2020. RandLA-Net： efficient semantic segmentation of large-scale point clouds//Proceedings of 2020 IEEE/ CVF Conference on Computer Vision and Pattern Recognition. Seattle， USA： IEEE： 11105-11114 ［ DOI： 10. 1109 / CVPR42600. 2020. 01112http://dx.doi.org/10.1109/CVPR42600.2020.01112］
Huang H， Bu Y， Xu H and Wang X. 2024. Point cloud segmentation algorithm based on contrastive learning and label mining. Journal of Computer Research and Development， 1-13
黄华，一凡，许宏丽，王晓荣. 2024. 基于对比学习和标签挖掘的点云分割算法. 计算机研究与发展， 1-13 ［DOI：10.7544/issn1000-1239.202330491http://dx.doi.org/10.7544/issn1000-1239.202330491］
Kong L， Liu Y， Chen R， Ma Y and Zhu X. 2023. Rethinking range view representation for LiDAR segmentation//Proceedings of 2023 IEEE/CVF International Conference on Computer Vision. Paris， France： IEEE： 228-240 ［DOI：10.1109/ICCV51070.2023.00028http://dx.doi.org/10.1109/ICCV51070.2023.00028］
Lai X， Liu J， Jiang L， Wang L and Zhao H. 2022. Stratified transformer for 3D point cloud segmentation//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans， LA， USA： IEEE： 8490-8499 ［DOI：10.1109/CVPR52688.2022.00831http://dx.doi.org/10.1109/CVPR52688.2022.00831］
Li L， Shum H P H， Breckon T P. 2023. Less is More： reducing task and model complexity for 3D point cloud semantic segmentation//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver， BC， Canada： IEEE： 9361-9371 ［DOI：10.1109/CVPR52729.2023.00903http://dx.doi.org/10.1109/CVPR52729.2023.00903］
Liu S Y， Chi J N， Wu C D and Xu F. 2023. Recurrent slice networks-based 3D point cloud-relevant integrated segmentation of semantic and instances. Journal of Image and Graphics，28（07）：2135-2150
刘苏毅，迟剑宁，吴成东，徐方. 2023. 基于递归切片网络的三维点云语义分割与实例分割. 中国图象图形学报， 28（07）：2135-2150［DOI：10. 11834/jig. 220154http://dx.doi.org/10.11834/jig.220154］
Liu S， Cao Y F， Huang W H and Li D D. 2023. LiDAR point cloud semantic segmentation combined with sparse attention and instance enhancement. Journal of Image and Graphics，28（02）：0483-0494
刘盛，曹益烽，黄文豪，李丁达. 2023. 融合稀疏注意力和实例增强的雷达点云分割. 中国图象图形学报，28（02）：0483-0494 ［DOI：10. 11834 / jig. 210787http://dx.doi.org/10.11834/jig.210787］
Liu Y， Fan B， Meng G， Lu J， Xiang S and Pan C. 2019. DensePoint： Learning Densely Contextual Representation for Efficient Point Cloud Processing// Proceedings of 2019 IEEE/CVF International Conference on Computer Vision （ICCV）. Seoul， Korea （South）： IEEE： 5238-5247 ［DOI：10.1109/ICCV.2019.00534http://dx.doi.org/10.1109/ICCV.2019.00534］
Liu Y， Yuan Y， Sun X and Li Z. 2023. A point cloud processing network combining local and global information. Journal of Zhejiang University （Science Edition）， 50（6）： 770-780
刘玉杰，原亚夫，孙晓瑞，李宗民. 2023. 局部信息和全局信息相结合的点云处理网络. 浙江大学学报（理学版），50（6）：770-780 ［DOI：10.3785/j.issn.1008-9497.2023.06.012http://dx.doi.org/10.3785/j.issn.1008-9497.2023.06.012］
Lu D， Xie Q， Wei M， Gao K， Xu L and Li J. 2022. Transformers in 3D Point Clouds： A Survey： arXiv：2205.07417［Z/OL］ ［DOI：10.48550/arXiv.2205.07417http://dx.doi.org/10.48550/arXiv.2205.07417］
Maturana D， Scherer S. 2015. VoxNet： A 3D convolutional neural network for real-time object recognition//Proceedings of 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems. Hamburg， Germany： IEEE： 922-928 ［DOI：10.1109/IROS.2015.7353481http://dx.doi.org/10.1109/IROS.2015.7353481］
Milioto A， Vizzo I， Behley J and Stachniss C. 2019. RangeNet ++： fast and accurate LiDAR semantic segmentation//Proceedings of 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems. Macau， China： IEEE： 4213-4220 ［DOI：10.1109/IROS40897.2019.8967762http://dx.doi.org/10.1109/IROS40897.2019.8967762］
Park C， Jeong Y， Cho M and Park J. 2022. Fast point transformer//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans， LA， USA： IEEE： 16928-16937 ［DOI：10.1109/CVPR52688.2022.01644http://dx.doi.org/10.1109/CVPR52688.2022.01644］
Park J， Kim C， Kim S and Jo K. 2023. PCSCNet： Fast 3D semantic segmentation of LiDAR point cloud for autonomous car using point convolution and sparse convolution network. EXPERT SYSTEMS WITH APPLICATIONS. 212 ［DOI：10.1016/j.eswa.2022.118815http://dx.doi.org/10.1016/j.eswa.2022.118815］
Qi C R， Su H， Mo K C and Guibas L J. 2017a. PointNet： deep learning on point sets for 3D classification and segmentation//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu， USA： IEEE： 77-85 ［DOI： 10. 1109 / CVPR. 2017. 16http://dx.doi.org/10.1109/CVPR.2017.16］
Qi C R， Yi L， Su H and Guibas L J. 2017b. Pointnet + + ： deep hierarchical feature learning on point sets in a metric space//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach， USA： NIPS： 5105-5114 ［DOI： 10. 5555 / 3295222. 3295263http://dx.doi.org/10.5555/3295222.3295263］
Riegler G， Ulusoy A O and Geiger A， 2017. OctNet： learning deep 3D representations at high resolutions//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu， HI， USA： IEEE：3577-3586 ［DOI： 10.1109/CVPR.2017.701http://dx.doi.org/10.1109/CVPR.2017.701］
Riz L， Saltori C， Ricci E and Poiesi F. 2023. Novel class discovery for 3D point cloud semantic segmentation//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver， BC， Canada： IEEE： 9393-9402 ［DOI：10.1109/CVPR52729.2023.00906http://dx.doi.org/10.1109/CVPR52729.2023.00906］
Song W， Cai W Y， He S Q and Li W J. 2021. Dynamic graph convolution with spatial attention for point cloud classification and segmentation. Journal of Image and Graphics，26（11）：2691-2702
宋巍，蔡万源，何盛琪，李文俊. 2021. 结合动态图卷积和空间注意力的点云分类与分割. 中国图象图形学报，26（11）：2691-2702 ［DOI：10. 11834 / jig. 200550http://dx.doi.org/10.11834/jig.200550］
Su H， Maji S， Kalogerakis E and Learned-Miller E. 2015. Multi-view convolutional neural networks for 3D shape recognition//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago， Chile： IEEE： 945-953 ［DOI： 10. 1109 / ICCV. 2015. 114http://dx.doi.org/10.1109/ICCV.2015.114］
Thomas H， Qi C R， Deschaud J E， Marcotegui B， Goulette F and Guibas L. 2019. Kpconv： flexible and deformable convolution for point clouds//Proceedings of 2019 IEEE/ CVF International Conference on Computer Vision. Seoul， Korea （South）： IEEE： 6410-6419 ［DOI： 10. 1109 / ICCV. 2019. 00651http://dx.doi.org/10.1109/ICCV.2019.00651］
Unal O， Dai D and Van Gool L， 2022. Scribble-Supervised LiDAR semantic segmentation// Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans， LA， USA： IEEE： 2687-2697 ［DOI：10.1109/CVPR52688.2022.00272http://dx.doi.org/10.1109/CVPR52688.2022.00272］
Wang L， Huang Y， Hou Y， Zhang S M and Shan J. 2019. Graph attention convolution for point cloud semantic segmentation//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach， CA， USA： IEEE： 10288-10297 ［DOI：10.1109/CVPR.2019.01054http://dx.doi.org/10.1109/CVPR.2019.01054］
Wang Y， Sun Y B， Liu Z W， Sarma S E， Bronstein M M and Solomon J M. 2019. Dynamic graph CNN for learning on point clouds. ACM Transactions on Graphics， 38 （ 5 ）： 146， 1-12 ［DOI： 10. 1145 / 3326362http://dx.doi.org/10.1145/3326362］
Wu J， Cui Y， Zhao X， Chen R and Xu G. 2022. SSA-PointNet++： A 3D point cloud semantic segmentation network under spatial self-attention mechanism. Journal of Computer-Aided Design & Computer Graphics， 34（3）： 437-448
吴军，崔玥，赵雪梅，陈睿星，徐刚. 2022. SSA-PointNet++：空间自注意力机制下的3D点云语义分割网络. 计算机辅助设计与图形学学报， 34（3）：437-448 ［DOI：10.3724/SP.J.1089.2022.18900http://dx.doi.org/10.3724/SP.J.1089.2022.18900］
Wu X， Lao Y， Jiang L， Liu X and Zhao H. 2022. Point Transformer V2： grouped vector attention and partition-based pooling//Advances in Neural Information Processing Systems. Curran Associates， Inc.： 33330-33342 ［DOI：10.48550/arxiv.2210.05666http://dx.doi.org/10.48550/arxiv.2210.05666］
Xu M， Ding R， Zhao H and Qi X. 2021. PAConv： Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds// Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Nashville， TN， USA： IEEE： 3172-3181 ［DOI：10.1109/CVPR46437.2021.00319http://dx.doi.org/10.1109/CVPR46437.2021.00319］
Yang J， Zhang C. 2024. Semantic segmentation of 3D point clouds based on boundary point estimation and sparse convolutional neural networks. Journal of Zhejiang University （Engineering Science Edition）， 58（6）： 1121-1132
杨军，张琛. 2024. 基于边界点估计与稀疏卷积神经网络的三维点云语义分割. 浙江大学学报（工学版）， 58（6）：1121-1132 ［DOI：10.3785/j.issn.1008-973X.2024.06.003http://dx.doi.org/10.3785/j.issn.1008-973X.2024.06.003］
Yang Y， Hayat M， Jin Z， Ren C and Lei Y. 2023. Geometry and uncertainty-aware 3D point cloud class-incremental semantic segmentation//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver， BC， Canada： IEEE： 21759-21768 ［DOI：10.1109/CVPR52729.2023.02084http://dx.doi.org/10.1109/CVPR52729.2023.02084］
Yu T， Meng J and Yuan J. 2018. Multi-view harmonized bilinear network for 3D object recognition//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City， UT： IEEE： 186-194 ［DOI：10.1109/CVPR.2018.00027http://dx.doi.org/10.1109/CVPR.2018.00027］
Yu X， Tang L， Rao Y， Huang T， Zhou J and Lu J. 2022. Point-BERT： pre-training 3D point cloud transformers with masked point modeling//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans， LA， USA： IEEE： 19291-19300 ［DOI：10.1109/CVPR52688.2022.01871http://dx.doi.org/10.1109/CVPR52688.2022.01871］
Zhang C， Wan H， Shen X and Wu Z. 2022a. PVT： point-voxel transformer for point cloud learning. INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS. 37（12）： 11985-12008. ［DOI：10.1002/int.23073http://dx.doi.org/10.1002/int.23073］
Zhang C， Wan H， Shen X and Wu Z. 2022b. PatchFormer： an efficient point transformer with patch attention//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans， LA， USA： IEEE： 11789-11798 ［DOI：10.1109/CVPR52688.2022.01150http://dx.doi.org/10.1109/CVPR52688.2022.01150］
Zhang J， Zhao X， Chen Z and Liu Z. 2019. A review of deep learning-based semantic segmentation for point cloud. IEEE Access. 7： 179118-179133 ［DOI：10.1109/ACCESS.2019.2958671http://dx.doi.org/10.1109/ACCESS.2019.2958671］
Zhang R， Wu Y， Jin W and Meng X. 2023. Deep-learning-based point cloud semantic segmentation： a survey. Electronics. 12（17）： 3642 ［DOI：10.3390/electronics12173642http://dx.doi.org/10.3390/electronics12173642］
Zhang Z， Yang B， Wang B and Li B. 2023. GrowSP： unsupervised semantic segmentation of 3D point clouds//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver， BC， Canada： IEEE： 17619-17629 ［DOI：10.1109/CVPR52729.2023.01690http://dx.doi.org/10.1109/CVPR52729.2023.01690］
Zhao B， Wang Z， Jia Z， Liang D and Liu Q. 2024. A 3D local feature descriptor based on dynamic graph convolution and pointNet. Journal of Computer-Aided Design & Computer Graphics， 1-11
赵宝，王梓涵，贾兆红，梁栋，刘强. 2024. 基于动态图卷积和PointNet的三维局部特征描述符. 计算机辅助设计与图形学学报， 1-11 ［DOI： 10.3724/SP.J.1089.2023-00083http://dx.doi.org/10.3724/SP.J.1089.2023-00083］
Zhao H， Jiang L， Fu C and Jia J. 2019. PointWeb： enhancing local neighborhood features for point cloud processing//Proceedings of 2019 IEEE/ CVF Conference on Computer Vision and Pattern Recognition. Long Beach， USA： IEEE： 5560-5568 ［ DOI： 10. 1109 / CVPR. 2019. 00571http://dx.doi.org/10.1109/CVPR.2019.00571］
Zhao H， Jiang L， Jia J， Torr P and Koltun V. 2021. Point Transformer//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision. Montreal， QC， Canada： IEEE：16259-16268 ［DOI：10.1109/ICCV48922.2021.01595http://dx.doi.org/10.1109/ICCV48922.2021.01595］
Zhang T， Yuan H， Qi L， Zhang J and Zhou Q. 2024. Point Cloud Mamba： Point Cloud Learning via State Space Model： arXiv：2403.00762［Z/OL］ ［DOI：10.48550/arXiv.2403.00762http://dx.doi.org/10.48550/arXiv.2403.00762］
相关文章
相关作者
相关机构
京公网安备11010802024621