{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T01:06:58Z","timestamp":1780362418273,"version":"3.54.1"},"reference-count":211,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["Grant No.: 61472444 and 61671470"],"award-info":[{"award-number":["Grant No.: 61472444 and 61671470"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Scientific and Technological Project of Henan Province","award":["NO. 232102211035"],"award-info":[{"award-number":["NO. 232102211035"]}]},{"name":"Foreign Expert Project of Ministry of Science and Technology of the People\u2019s Republic of China","award":["G2023026004L"],"award-info":[{"award-number":["G2023026004L"]}]},{"name":"Henan Province Key R&D Special Project","award":["231111112700"],"award-info":[{"award-number":["231111112700"]}]},{"name":"\u201cZHONGYUAN Talent Program\u201d","award":["ZYYCYU202012112"],"award-info":[{"award-number":["ZYYCYU202012112"]}]},{"name":"Water Conservancy Equipment and Intelligent Operation & Maintenance Engineering Technology Research Centre in Henan Province","award":["Yukeshi2024-01"],"award-info":[{"award-number":["Yukeshi2024-01"]}]},{"name":"Henan International Joint Laboratory of Thermo-Fluid Electro Chemical System for New Energy Vehicle","award":["Yuke2020-23"],"award-info":[{"award-number":["Yuke2020-23"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s10489-025-06854-y","type":"journal-article","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T02:48:32Z","timestamp":1759200512000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep learning techniques for point cloud tasks: a review"],"prefix":"10.1007","volume":"55","author":[{"given":"Xiaona","family":"Song","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haozhe","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinxing","family":"Niu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"Nian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruixue","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,30]]},"reference":[{"key":"6854_CR1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3005434","author":"Y Guo","year":"2021","unstructured":"Guo Y, Wang H, Hu Q, Liu H, Liu L, Bennamoun M (2021) Deep learning for 3d point clouds: A survey. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/TPAMI.2020.3005434","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"17","key":"6854_CR2","doi-asserted-by":"publisher","first-page":"3642","DOI":"10.3390\/electronics12173642","volume":"12","author":"R Zhang","year":"2023","unstructured":"Zhang R, Wu Y, Jin W, Meng X (2023) Deep-learning-based point cloud semantic segmentation: A survey. Electronics 12(17):3642. https:\/\/doi.org\/10.3390\/electronics12173642","journal-title":"Electronics"},{"issue":"24","key":"6854_CR3","doi-asserted-by":"publisher","first-page":"9577","DOI":"10.3390\/s22249577","volume":"22","author":"SY Alaba","year":"2022","unstructured":"Alaba SY, Ball JE (2022) A survey on deep-learning-based lidar 3d object detection for autonomous driving. Sensors 22(24):9577. https:\/\/doi.org\/10.3390\/s22249577","journal-title":"Sensors"},{"key":"6854_CR4","doi-asserted-by":"publisher","unstructured":"Han B, Ma JW, Leite F (2021) A framework for semi-automatically identifying fully occluded objects in 3d models: Towards comprehensive construction design review in virtual reality. Adv Eng Inform 50:101398. https:\/\/doi.org\/10.1016\/j.aei.2021.101398","DOI":"10.1016\/j.aei.2021.101398"},{"key":"6854_CR5","doi-asserted-by":"publisher","unstructured":"Nguyen M, Vats S, Damme S, Hooft J, Vega MT, Wauters T, De Turck F, Timmerer C, Hellwagner H (2023) Characterization of the quality of experience and immersion of point cloud videos in augmented reality through a subjective study. IEEE Access 11:128898\u2013128910. https:\/\/doi.org\/10.1109\/ACCESS.2023.3326374","DOI":"10.1109\/ACCESS.2023.3326374"},{"key":"6854_CR6","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.isprsjprs.2015.01.011","volume":"104","author":"A-V Vo","year":"2015","unstructured":"Vo A-V, Truong-Hong L, Laefer DF, Bertolotto M (2015) Octree-based region growing for point cloud segmentation. ISPRS J Photogramm Remote Sens 104:88\u2013100. https:\/\/doi.org\/10.1016\/j.isprsjprs.2015.01.011","journal-title":"ISPRS J Photogramm Remote Sens"},{"issue":"19","key":"6854_CR7","doi-asserted-by":"publisher","first-page":"4188","DOI":"10.3390\/s19194188","volume":"19","author":"W Liu","year":"2019","unstructured":"Liu W, Sun J, Li W, Hu T, Wang P (2019) Deep learning on point clouds and its application: A survey. Sensors 19(19):4188. https:\/\/doi.org\/10.3390\/s19194188","journal-title":"Sensors"},{"issue":"11","key":"6854_CR8","doi-asserted-by":"publisher","first-page":"1729","DOI":"10.3390\/rs12111729","volume":"12","author":"SA Bello","year":"2020","unstructured":"Bello SA, Yu S, Wang C, Adam JM, Li J (2020) Review: Deep learning on 3d point clouds. Remote Sensing 12(11):1729. https:\/\/doi.org\/10.3390\/rs12111729","journal-title":"Remote Sensing"},{"key":"6854_CR9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3195555","author":"B Fei","year":"2022","unstructured":"Fei B, Yang W, Chen W, Li Z, Li Y, Ma T, Hu X, Ma L (2022) Comprehensive review of deep learning-based 3d point clouds completion processing and analysis. IEEE Trans Intell Transp Syst. https:\/\/doi.org\/10.1109\/TITS.2022.3195555","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"6854_CR10","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1016\/j.isprsjprs.2024.01.017","volume":"208","author":"P Wei","year":"2024","unstructured":"Wei P, Yan L, Xie H, Qiu D, Qiu C, Wu H, Zhao Y, Hu X, Huang M (2024) Lidenerf: Neural radiance field reconstruction with depth prior provided by lidar point cloud. ISPRS J Photogramm Remote Sens 208:296\u2013307. https:\/\/doi.org\/10.1016\/j.isprsjprs.2024.01.017","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"6854_CR11","doi-asserted-by":"publisher","first-page":"2250","DOI":"10.1109\/LSP.2024.3452556","volume":"31","author":"W Xie","year":"2024","unstructured":"Xie W, Liu Y, Wang K, Wang M (2024) Llm-guided cross-modal point cloud quality assessment: A graph learning approach. IEEE Signal Process Lett 31:2250\u20132254. https:\/\/doi.org\/10.1109\/LSP.2024.3452556","journal-title":"IEEE Signal Process Lett"},{"key":"6854_CR12","doi-asserted-by":"publisher","unstructured":"Sarker S, Sarker P, Stone G, Gorman R, Tavakkoli A, Bebis G, Sattarvand J (2024) A comprehensive overview of deep learning techniques for 3d point cloud classification and semantic segmentation. Mach Vis Appl 35(4). https:\/\/doi.org\/10.1007\/s00138-024-01543-1","DOI":"10.1007\/s00138-024-01543-1"},{"key":"6854_CR13","doi-asserted-by":"publisher","unstructured":"Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? the kitti vision benchmark suite. 2012 IEEE Conference on computer vision and pattern recognition. https:\/\/doi.org\/10.1109\/CVPR.2012.6248074","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"6854_CR14","doi-asserted-by":"publisher","unstructured":"Wu Z, Song S, Khosla A, Yu F, Zhang L, Tang X, Xiao J (2015) 3d shapenets: A deep representation for volumetric shapes. Comput Vis Patt Recogn. https:\/\/doi.org\/10.1109\/CVPR.2015.7298801","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"6854_CR15","doi-asserted-by":"publisher","unstructured":"Li D, Lu C, Chen Z, Guan J, Zhao J, Du J (2024) Graph neural networks in point clouds: A survey. Remote Sens 16(14):2518. https:\/\/doi.org\/10.3390\/rs16142518","DOI":"10.3390\/rs16142518"},{"key":"6854_CR16","doi-asserted-by":"publisher","unstructured":"Tychola KA, Vrochidou E, Papakostas GA (2024) Deep learning based computer vision under the prism of 3d point clouds: a systematic review. Vis Comput. https:\/\/doi.org\/10.1007\/s00371-023-03237-7","DOI":"10.1007\/s00371-023-03237-7"},{"key":"6854_CR17","doi-asserted-by":"publisher","unstructured":"Qi CR, Su H, Mo K, Guibas LJ (2017) Pointnet: Deep learning on point sets for 3d classification and segmentation. 2017 IEEE Conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/CVPR.2017.16","DOI":"10.1109\/CVPR.2017.16"},{"key":"6854_CR18","doi-asserted-by":"publisher","unstructured":"Qi CR, Yi L, Su H, Guibas LJ (2017) Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Neural Inform Process Syst. https:\/\/doi.org\/10.48550\/arXiv.1706.02413","DOI":"10.48550\/arXiv.1706.02413"},{"key":"6854_CR19","doi-asserted-by":"publisher","unstructured":"Wang Y, Sun Y, Liu Z, Sarma SE, Bronstein MM, Solomon JM (2019) Dynamic graph cnn for learning on point clouds. Association Comput Mach (5). https:\/\/doi.org\/10.1145\/3326362","DOI":"10.1145\/3326362"},{"key":"6854_CR20","doi-asserted-by":"publisher","unstructured":"Chen R, Cong Y (2022) The devil is in the pose: Ambiguity-free 3d rotation-invariant learning via pose-aware convolution. 2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), 7462\u20137471. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00732","DOI":"10.1109\/CVPR52688.2022.00732"},{"key":"6854_CR21","doi-asserted-by":"publisher","unstructured":"Chen Y, Duan L, Zhao S, Ding C, Tao D (2024) Local-consistent transformation learning for rotation-invariant point cloud analysis. In: 2024 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 5418\u20135427. https:\/\/doi.org\/10.1109\/CVPR52733.2024.00518","DOI":"10.1109\/CVPR52733.2024.00518"},{"key":"6854_CR22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00910","author":"B Fan","year":"2019","unstructured":"Fan B, Pan C, Xiang S, Liu Y (2019) Relation-shape convolutional neural network for point cloud analysis. Comput Vis Pattern Recogn. https:\/\/doi.org\/10.1109\/CVPR.2019.00910","journal-title":"Comput Vis Pattern Recogn"},{"key":"6854_CR23","doi-asserted-by":"publisher","unstructured":"Thomas H, Qi CR, Deschaud JE, Marcotegui B, Guibas LJ (2019) Kpconv: Flexible and deformable convolution for point clouds. 2019 IEEE\/CVF International conference on computer vision (ICCV). https:\/\/doi.org\/10.48550\/arXiv.1904.08889","DOI":"10.48550\/arXiv.1904.08889"},{"key":"6854_CR24","doi-asserted-by":"publisher","unstructured":"Su H, Maji S, Kalogerakis E, Learned-Miller E (2015) Multi-view convolutional neural networks for 3d shape recognition. 2015 IEEE International conference on computer vision (ICCV). https:\/\/doi.org\/10.1109\/ICCV.2015.114","DOI":"10.1109\/ICCV.2015.114"},{"issue":"6","key":"6854_CR25","doi-asserted-by":"publisher","first-page":"6844","DOI":"10.1007\/s10489-022-03930-5","volume":"53","author":"A Jhaldiyal","year":"2023","unstructured":"Jhaldiyal A, Chaudhary N (2023) Semantic segmentation of 3d lidar data using deep learning: a review of projection-based methods. Appl Intell 53(6):6844\u20136855. https:\/\/doi.org\/10.1007\/s10489-022-03930-5","journal-title":"Appl Intell"},{"key":"6854_CR26","doi-asserted-by":"publisher","unstructured":"Maturana D, Scherer S (2015) Voxnet: A 3d convolutional neural network for real-time object recognition. 2015 IEEE\/RSJ International conference on intelligent robots and systems (IROS). https:\/\/doi.org\/10.1109\/IROS.2015.7353481","DOI":"10.1109\/IROS.2015.7353481"},{"key":"6854_CR27","doi-asserted-by":"publisher","unstructured":"Zhou Y, Tuzel O (2017) Voxelnet: End-to-end learning for point cloud based 3d object detection. 2018 IEEE\/CVF Conference on computer vision and pattern recognition, 4490\u20134499. https:\/\/doi.org\/10.1109\/CVPR.2018.00472","DOI":"10.1109\/CVPR.2018.00472"},{"key":"6854_CR28","doi-asserted-by":"publisher","unstructured":"Zhang Y, Rabbat M (2018) A graph-cnn for 3d point cloud classification. 2018 IEEE International conference on acoustics, speech and signal processing (ICASSP). https:\/\/doi.org\/10.1109\/ICASSP.2018.8462291","DOI":"10.1109\/ICASSP.2018.8462291"},{"issue":"2","key":"6854_CR29","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/s41095-021-0229-5","volume":"7","author":"M-H Guo","year":"2021","unstructured":"Guo M-H, Cai J-X, Liu Z-N, Mu T-J, Martin RR, Hu S-M (2021) Pct: Point cloud transformer. Comput Vis Media 7(2):187\u2013199. https:\/\/doi.org\/10.1007\/s41095-021-0229-5","journal-title":"Comput Vis Media"},{"key":"6854_CR30","doi-asserted-by":"publisher","unstructured":"Zhao H, Jiang L, Jia J, Torr P, Koltun V (2021) Point transformer. 2021 IEEE\/CVF International conference on computer vision (ICCV), 16239\u201316248. https:\/\/doi.org\/10.1109\/ICCV48922.2021.01595","DOI":"10.1109\/ICCV48922.2021.01595"},{"issue":"4","key":"6854_CR31","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/MGRS.2019.2937630","volume":"8","author":"Y Xie","year":"2020","unstructured":"Xie Y, Tian J, Zhu XX (2020) Linking points with labels in 3d: A review of point cloud semantic segmentation. IEEE Geosci Remote Sens Mag 8(4):38\u201359. https:\/\/doi.org\/10.1109\/MGRS.2019.2937630","journal-title":"IEEE Geosci Remote Sens Mag"},{"key":"6854_CR32","doi-asserted-by":"publisher","unstructured":"Dai A, Chang AX, Savva M, Halber M, Funkhouser T, Niener M (2017) Scannet: Richly-annotated 3d reconstructions of indoor scenes. 2017 IEEE Conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.48550\/arXiv.1702.04405","DOI":"10.48550\/arXiv.1702.04405"},{"key":"6854_CR33","doi-asserted-by":"publisher","unstructured":"Caesar H, Bankiti V, Lang AH, Vora S, Beijbom O (2019) nuscenes: A multimodal dataset for autonomous driving. https:\/\/doi.org\/10.1109\/cvpr42600.2020.01164","DOI":"10.1109\/cvpr42600.2020.01164"},{"key":"6854_CR34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170","author":"I Armeni","year":"2016","unstructured":"Armeni I, Sener O, Zamir A, Jiang H, Brilakis I, Fischer M, Savarese S (2016) IEEE: 3d semantic parsing of large-scale indoor spaces. IEEE Comput Soc. https:\/\/doi.org\/10.1109\/CVPR.2016.170","journal-title":"IEEE Comput Soc"},{"key":"6854_CR35","doi-asserted-by":"publisher","unstructured":"Hackel T, Savinov N, Ladicky L, Wegner JD, Schindler K, Pollefeys M (2017) Semantic3d.net: A new large-scale point cloud classification benchmark. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences. https:\/\/doi.org\/10.5194\/isprs-annals-IV-1-W1-91-2017","DOI":"10.5194\/isprs-annals-IV-1-W1-91-2017"},{"key":"6854_CR36","doi-asserted-by":"crossref","unstructured":"Behley J, Garbade M, Milioto A, Quenzel J, Behnke S, Stachniss C, Gall J (2020) Semantickitti: A dataset for semantic scene understanding of lidar sequences. 2019 IEEE\/CVF International conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2019.00939"},{"key":"6854_CR37","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1080\/01431161.2023.2297177","volume":"45","author":"D Singh","year":"2024","unstructured":"Singh D, Yadav M (2024) Deep learning-based semantic segmentation of three-dimensional point cloud: a comprehensive review. Int J Remote Sens 45:532\u2013586. https:\/\/doi.org\/10.1080\/01431161.2023.2297177","journal-title":"Int J Remote Sens"},{"key":"6854_CR38","doi-asserted-by":"publisher","unstructured":"Cheng B, Girshick R, Doll\u00e1r P, Berg AC, Kirillov A (2021) Boundary iou: Improving object-centric image segmentation evaluation. In: 2021 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp. 15329\u201315337. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01508","DOI":"10.1109\/CVPR46437.2021.01508"},{"key":"6854_CR39","doi-asserted-by":"publisher","unstructured":"Qian G, Li Y, Peng H, Mai J, Hammoud H, Elhoseiny M, Ghanem B (2022) Pointnext: Revisiting pointnet++ with improved training and scaling strategies. ArXiv. abs\/2206.04670, https:\/\/doi.org\/10.48550\/arXiv.2206.04670","DOI":"10.48550\/arXiv.2206.04670"},{"key":"6854_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592131","volume":"42","author":"P-S Wang","year":"2023","unstructured":"Wang P-S (2023) Octformer: Octree-based transformers for 3d point clouds. ACM Trans on Graph 42:1\u201311. https:\/\/doi.org\/10.1145\/3592131","journal-title":"ACM Trans on Graph"},{"key":"6854_CR41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00344","author":"J Yang","year":"2019","unstructured":"Yang J, Zhang Q, Ni B, Li L, Tian Q (2019) Modeling point clouds with self-attention and gumbel subset sampling. Comput Vis Pattern Recogn. https:\/\/doi.org\/10.1109\/CVPR.2019.00344","journal-title":"Comput Vis Pattern Recogn"},{"key":"6854_CR42","doi-asserted-by":"publisher","unstructured":"Zhang H, Wang C, Tian S, Lu B, Zhang L, Ning X, Bai X (2023) Deep learning-based 3d point cloud classification: A systematic survey and outlook. Displays, 79. https:\/\/doi.org\/10.1016\/j.displa.2023.102456","DOI":"10.1016\/j.displa.2023.102456"},{"key":"6854_CR43","doi-asserted-by":"publisher","unstructured":"Feng Y, Zhang Z, Zhao X, Ji R, Gao Y (2018) Gvcnn: Group-view convolutional neural networks for 3d shape recognition. 2018 IEEE\/CVF Conference on computer vision and pattern recognition. https:\/\/doi.org\/10.1109\/CVPR.2018.00035","DOI":"10.1109\/CVPR.2018.00035"},{"key":"6854_CR44","doi-asserted-by":"publisher","unstructured":"Yu T, Meng J, Yuan J (2018) Multi-view harmonized bilinear network for 3d object recognition. 2018 IEEE\/CVF Conference on computer vision and pattern recognition. https:\/\/doi.org\/10.1109\/CVPR.2018.00027","DOI":"10.1109\/CVPR.2018.00027"},{"key":"6854_CR45","doi-asserted-by":"publisher","unstructured":"Wei X, Yu R, Sun J (2020) View-gcn: View-based graph convolutional network for 3d shape analysis. 2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00192","DOI":"10.1109\/CVPR42600.2020.00192"},{"key":"6854_CR46","doi-asserted-by":"publisher","unstructured":"Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. Int Conf Learn Represent. https:\/\/doi.org\/10.48550\/arXiv.1609.02907","DOI":"10.48550\/arXiv.1609.02907"},{"key":"6854_CR47","doi-asserted-by":"publisher","unstructured":"Hamdi A, Giancola S, Li B, Thabet A, Ghanem B (2020) Mvtn: Multi-view transformation network for 3d shape recognition. ICCV 2021. https:\/\/doi.org\/10.48550\/arXiv.2011.13244","DOI":"10.48550\/arXiv.2011.13244"},{"key":"6854_CR48","doi-asserted-by":"publisher","unstructured":"Riegler G, Ulusoy AO, Geiger A (2017) Octnet: Learning deep 3d representations at high resolutions.\u00a0Comput Vis Pattern Recogn. https:\/\/doi.org\/10.1109\/CVPR.2017.701","DOI":"10.1109\/CVPR.2017.701"},{"key":"6854_CR49","doi-asserted-by":"publisher","unstructured":"Klokov R, Lempitsky V (2017) Escape from cells: Deep kd-networks for the recognition of 3d point cloud models. 2017 IEEE International conference on computer vision (ICCV). https:\/\/doi.org\/10.1109\/ICCV.2017.99","DOI":"10.1109\/ICCV.2017.99"},{"key":"6854_CR50","doi-asserted-by":"publisher","unstructured":"Hanocka R, Hertz A, Fish N, Giryes R, Fleishman S, Cohen-Or D (2019) Meshcnn: A network with an edge. ACM Trans Graph 38(4CD), 90\u201319012. https:\/\/doi.org\/10.1145\/3306346.3322959","DOI":"10.1145\/3306346.3322959"},{"key":"6854_CR51","doi-asserted-by":"publisher","unstructured":"Meng HY, Gao L, Lai YK, Manocha D (2019) Vv-net: Voxel vae net with group convolutions for point cloud segmentation. 2019 IEEE\/CVF International conference on computer vision (ICCV). https:\/\/doi.org\/10.1109\/ICCV.2019.00859","DOI":"10.1109\/ICCV.2019.00859"},{"key":"6854_CR52","doi-asserted-by":"publisher","unstructured":"Janvier M (2023) Group equivariant convolutional networks. Int Conf Mach Learn. https:\/\/doi.org\/10.48550\/arXiv.1602.07576","DOI":"10.48550\/arXiv.1602.07576"},{"key":"6854_CR53","doi-asserted-by":"publisher","unstructured":"Li J, Chen BM, Lee GH (2018) So-net: Self-organizing network for point cloud analysis. 2018 IEEE\/CVF Conference on computer vision and pattern recognition. https:\/\/doi.org\/10.1109\/CVPR.2018.00979","DOI":"10.1109\/CVPR.2018.00979"},{"key":"6854_CR54","doi-asserted-by":"publisher","unstructured":"Zhao H, Jiang L, Fu CW, Jia J (2019) Pointweb: Enhancing local neighborhood features for point cloud processing. 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/CVPR.2019.00571","DOI":"10.1109\/CVPR.2019.00571"},{"key":"6854_CR55","doi-asserted-by":"publisher","unstructured":"Yan X, Zheng C, Li Z, Wang S, Cui S (2020) Pointasnl: Robust point clouds processing using nonlocal neural networks with adaptive sampling.\u00a0Comput Vis Pattern Recogn. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00563","DOI":"10.1109\/CVPR42600.2020.00563"},{"key":"6854_CR56","doi-asserted-by":"publisher","unstructured":"Xu M, Ding R, Zhao H, Qi X (2021) Paconv: Position adaptive convolution with dynamic kernel assembling on point clouds. Comput Vis Pattern Recogn. https:\/\/doi.org\/10.48550\/arXiv.2103.14635","DOI":"10.48550\/arXiv.2103.14635"},{"key":"6854_CR57","doi-asserted-by":"publisher","unstructured":"Ma X, Qin C, You H, Ran H, Fu Y (2022) Rethinking network design and local geometry in point cloud: A simple residual mlp framework. Int Conf Learn Represent. https:\/\/doi.org\/10.48550\/arXiv.2202.07123","DOI":"10.48550\/arXiv.2202.07123"},{"key":"6854_CR58","doi-asserted-by":"publisher","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. 2018 IEEE\/CVF Conference on computer vision and pattern recognition. https:\/\/doi.org\/10.1109\/CVPR.2018.00474","DOI":"10.1109\/CVPR.2018.00474"},{"key":"6854_CR59","doi-asserted-by":"publisher","unstructured":"Xue L, Yu N, Zhang S, Li J, Mart\u2019in-Mart\u2019in R, Wu J, Xiong C, Xu R, Niebles JC, Savarese S (2023) Ulip-2: Towards scalable multimodal pre-training for 3d understanding. ArXiv. abs\/2305.08275, https:\/\/doi.org\/10.48550\/arXiv.2305.08275","DOI":"10.48550\/arXiv.2305.08275"},{"issue":"2","key":"6854_CR60","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1007\/s00530-024-01303-1","volume":"30","author":"W Zhao","year":"2024","unstructured":"Zhao W, Jia L, Zhai H, Chai S, Li P (2024) Pointsgln: a novel point cloud classification network based on sampling grouping and local point normalization. Multimedia Syst 30(2):106. https:\/\/doi.org\/10.1007\/s00530-024-01303-1","journal-title":"Multimedia Syst"},{"issue":"9","key":"6854_CR61","doi-asserted-by":"publisher","first-page":"2254","DOI":"10.3390\/rs15092254","volume":"15","author":"H Lai","year":"2023","unstructured":"Lai H, Law KLE (2023) Efficient point cloud object classifications with ghostmlp. Remote Sens 15(9):2254. https:\/\/doi.org\/10.3390\/rs15092254","journal-title":"Remote Sens"},{"key":"6854_CR62","doi-asserted-by":"publisher","unstructured":"Hua BS, Tran MK, Yeung SK (2017) Pointwise convolutional neural networks. 2018 IEEE\/CVF Conference on computer vision and pattern recognition. https:\/\/doi.org\/10.1109\/CVPR.2018.00109","DOI":"10.1109\/CVPR.2018.00109"},{"key":"6854_CR63","doi-asserted-by":"publisher","unstructured":"Li Y, Bu R, Sun M, Wu W, Di X, Chen B (2018) Pointcnn: convolution on x transformed points. Neural Inform Process Syst. https:\/\/doi.org\/10.48550\/arXiv.1801.07791","DOI":"10.48550\/arXiv.1801.07791"},{"key":"6854_CR64","doi-asserted-by":"publisher","unstructured":"Komarichev A, Zhong Z, Hua J (2020) A-cnn: Annularly convolutional neural networks on point clouds. Computer Vision and Pattern Recognition. https:\/\/doi.org\/10.1109\/CVPR.2019.00760","DOI":"10.1109\/CVPR.2019.00760"},{"key":"6854_CR65","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.cag.2020.02.005","volume":"88","author":"A Boulch","year":"2020","unstructured":"Boulch A (2020) Convpoint: Continuous convolutions for point cloud processing. Comput Graph 88:24\u201334. https:\/\/doi.org\/10.1016\/j.cag.2020.02.005","journal-title":"Comput Graph"},{"key":"6854_CR66","doi-asserted-by":"publisher","unstructured":"Ran H, Zhuo W, Liu J, Lu L (2021) Learning inner-group relations on point clouds. IEEE Int Conf Comput Vis. https:\/\/doi.org\/10.48550\/arXiv.2108.12468","DOI":"10.48550\/arXiv.2108.12468"},{"key":"6854_CR67","doi-asserted-by":"publisher","unstructured":"Zhang H, Wang K, Zhong C, Yun K, Wang Z, Yang Y, Tao X (2024) Lspconv: local spatial projection convolution for point cloud analysis. PeerJ Comput Sci 10. https:\/\/doi.org\/10.7717\/peerj-cs.1738","DOI":"10.7717\/peerj-cs.1738"},{"issue":"3","key":"6854_CR68","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1007\/s13042-023-01940-4","volume":"15","author":"X Meng","year":"2024","unstructured":"Meng X, Lu X, Ye H, Yang B, Cao F (2024) A new self-augment cnn for 3d point cloud classification and segmentation. Int J Mach Learn Cybern 15(3):807\u2013818. https:\/\/doi.org\/10.1007\/s13042-023-01940-4","journal-title":"Int J Mach Learn Cybern"},{"key":"6854_CR69","doi-asserted-by":"publisher","unstructured":"Zhang K, Hao M, Wang J, De\u00a0Silva CW, Fu C (2019) Linked dynamic graph cnn: Learning on point cloud via linking hierarchical features. 2021 27th International conference on mechatronics and machine vision in practice (M2VIP). https:\/\/doi.org\/10.48550\/arXiv.1904.10014","DOI":"10.48550\/arXiv.1904.10014"},{"key":"6854_CR70","doi-asserted-by":"publisher","unstructured":"Xu Q, Sun X, Wu CY, Wang P, Neumann U (2020) Grid-gcn for fast and scalable point cloud learning. 2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00570","DOI":"10.1109\/CVPR42600.2020.00570"},{"key":"6854_CR71","doi-asserted-by":"publisher","unstructured":"Mohammadi SS, Wang Y, Bue AD (2021) Pointview-gcn: 3d shape classification with multi-view point clouds. Int Conf Inform Photonics. https:\/\/doi.org\/10.1109\/ICIP42928.2021.9506426","DOI":"10.1109\/ICIP42928.2021.9506426"},{"key":"6854_CR72","doi-asserted-by":"publisher","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. Comput Sci. https:\/\/doi.org\/10.48550\/arXiv.1409.1556","DOI":"10.48550\/arXiv.1409.1556"},{"key":"6854_CR73","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.neucom.2020.10.086","volume":"429","author":"R Li","year":"2021","unstructured":"Li R, Zhang Y, Niu D, Yang G, Zafar N, Zhang C, Zhao X (2021) Pointvgg: Graph convolutional network with progressive aggregating features on point clouds. Neurocomputing 429:187\u2013198. https:\/\/doi.org\/10.1016\/j.neucom.2020.10.086","journal-title":"Neurocomputing"},{"key":"6854_CR74","doi-asserted-by":"publisher","unstructured":"Zhou H, Feng Y, Fang M, Wei M, Qin J, Lu T (2021) Adaptive graph convolution for point cloud analysis. 2021 IEEE\/CVF International conference on computer vision (ICCV), 4945\u20134954. https:\/\/doi.org\/10.48550\/arXiv.2108.08035","DOI":"10.48550\/arXiv.2108.08035"},{"issue":"2","key":"6854_CR75","doi-asserted-by":"publisher","first-page":"617","DOI":"10.3390\/s24020617","volume":"24","author":"Y Yue","year":"2024","unstructured":"Yue Y, Li X, Peng Y (2024) A 3d point cloud classification method based on adaptive graph convolution and global attention. Sensors 24(2):617. https:\/\/doi.org\/10.3390\/s24020617","journal-title":"Sensors"},{"key":"6854_CR76","doi-asserted-by":"publisher","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. arXiv https:\/\/doi.org\/10.48550\/arXiv.1706.03762","DOI":"10.48550\/arXiv.1706.03762"},{"key":"6854_CR77","doi-asserted-by":"publisher","first-page":"5638","DOI":"10.1109\/TMM.2022.3198318","volume":"25","author":"X-F Han","year":"2023","unstructured":"Han X-F, Jin Y-F, Cheng H-X, Xiao G-Q (2023) Dual transformer for point cloud analysis. IEEE Trans Multimedia 25:5638\u20135648. https:\/\/doi.org\/10.1109\/TMM.2022.3198318","journal-title":"IEEE Trans Multimedia"},{"key":"6854_CR78","doi-asserted-by":"publisher","unstructured":"Wu X, Lao Y, Jiang L, Liu X, Zhao H (2022) Point transformer v2: Grouped vector attention and partition-based pooling. Neural Inform Process Syst. https:\/\/doi.org\/10.48550\/arXiv.2210.05666","DOI":"10.48550\/arXiv.2210.05666"},{"key":"6854_CR79","doi-asserted-by":"crossref","unstructured":"Zhang C, Wan H, Shen X, Wu Z (2022) PVT: Point-Voxel Transformer for Point Cloud Learning. arXiv:2108.06076","DOI":"10.1002\/int.23073"},{"key":"6854_CR80","doi-asserted-by":"publisher","unstructured":"Chen G-S, Wang M, Yang Y, Yu K, Yuan L, Yue Y (2023) Pointgpt: Auto-regressively generative pre-training from point clouds. Neural Inform Process Syst. https:\/\/doi.org\/10.48550\/arXiv.2305.11487","DOI":"10.48550\/arXiv.2305.11487"},{"key":"6854_CR81","doi-asserted-by":"publisher","unstructured":"Wang W, Zheng VW, Yu H, Miao C (2019) A survey of zero-shot learning: Settings, methods, and applications. ACM Trans Intell Syst Technol 10(2). https:\/\/doi.org\/10.1145\/3293318","DOI":"10.1145\/3293318"},{"key":"6854_CR82","doi-asserted-by":"publisher","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J (2021) Learning transferable visual models from natural language supervision. Comput Sci. https:\/\/doi.org\/10.48550\/arXiv.2103.00020","DOI":"10.48550\/arXiv.2103.00020"},{"key":"6854_CR83","doi-asserted-by":"publisher","unstructured":"Zhang R, Guo Z, Zhang W, Li K, Miao X, Cui B, Qiao Y, Gao P, Li H (2021) Pointclip: Point cloud understanding by clip. 2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00836","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"6854_CR84","doi-asserted-by":"publisher","unstructured":"Zhu X, Zhang R, He B, Zeng Z, Zhang S, Gao P (2022) Pointclip v2: Adapting clip for powerful 3d open-world learning. ArXiv. abs\/2211.11682. https:\/\/doi.org\/10.48550\/arXiv.2211.11682","DOI":"10.48550\/arXiv.2211.11682"},{"key":"6854_CR85","doi-asserted-by":"publisher","unstructured":"Yu X, Tang L, Rao Y, Huang T, Zhou J, Lu J (2021) Point-bert: Pre-training 3d point cloud transformers with masked point modeling. 2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.48550\/arXiv.2111.14819","DOI":"10.48550\/arXiv.2111.14819"},{"key":"6854_CR86","doi-asserted-by":"crossref","unstructured":"Pang Y, Wang W, Tay FEH, Liu W, Tian Y, Yuan L (2022) Masked Autoencoders for Point Cloud Self-supervised Learning. arXiv:2203.06604","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"6854_CR87","doi-asserted-by":"publisher","unstructured":"Jia M, Tang L, Chen BC, Cardie C, Belongie S, Hariharan B, Lim SN (2022) Visual prompt tuning. Comput Vis \u2013 ECCV 2022. https:\/\/doi.org\/10.48550\/arXiv.2203.12119","DOI":"10.48550\/arXiv.2203.12119"},{"key":"6854_CR88","doi-asserted-by":"publisher","unstructured":"Zha Y, Wang J, Dai T, Chen B, Wang Z, Xia S-T (2023) Instance-aware dynamic prompt tuning for pre-trained point cloud models. 2023 IEEE\/CVF International conference on computer vision (ICCV). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01302","DOI":"10.1109\/ICCV51070.2023.01302"},{"key":"6854_CR89","doi-asserted-by":"publisher","unstructured":"Afham M, Dissanayake I, Dissanayake D, Dharmasiri A, Thilakarathna K, Rodrigo R (2022) Crosspoint: Self-supervised cross-modal contrastive learning for 3d point cloud understanding. Comput Vis Pattern Recogn. https:\/\/doi.org\/10.48550\/arXiv.2203.00680","DOI":"10.48550\/arXiv.2203.00680"},{"key":"6854_CR90","doi-asserted-by":"publisher","unstructured":"Baevski A, Hsu WN, Xu Q, Babu A, Gu J, Auli M (2022) data2vec: A general framework for self-supervised learning in speech, vision and language. Int Conf Mach Learn. https:\/\/doi.org\/10.48550\/arXiv.2202.03555","DOI":"10.48550\/arXiv.2202.03555"},{"key":"6854_CR91","doi-asserted-by":"publisher","unstructured":"Zeid KA, Schult J, Hermans A, Leibe B (2024) Point2vec for self-supervised representation learning on point clouds. Pattern Recogn pp 131\u2013146. https:\/\/doi.org\/10.48550\/arXiv.2303.16570","DOI":"10.48550\/arXiv.2303.16570"},{"issue":"13","key":"6854_CR92","doi-asserted-by":"publisher","first-page":"2453","DOI":"10.3390\/rs16132453","volume":"16","author":"Y Xiao","year":"2024","unstructured":"Xiao Y, Dou Y, Yang S (2024) Pointblip: Zero-training point cloud classification network based on blip-2 model. Remote Sens 16(13):2453. https:\/\/doi.org\/10.3390\/rs16132453","journal-title":"Remote Sens"},{"issue":"4","key":"6854_CR93","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1177\/01423312221093147","volume":"45","author":"Z Liang","year":"2023","unstructured":"Liang Z, Huang Y (2023) Survey on deep learning-based 3d object detection in autonomous driving. Trans Inst Meas Control 45(4):761\u2013776. https:\/\/doi.org\/10.1177\/01423312221093147","journal-title":"Trans Inst Meas Control"},{"key":"6854_CR94","doi-asserted-by":"publisher","unstructured":"Li B, Zhang T, Xia T (2016) Vehicle detection from 3d lidar using fully convolutional network. Robot Sci Syst. https:\/\/doi.org\/10.15607\/RSS.2016.XII.042","DOI":"10.15607\/RSS.2016.XII.042"},{"key":"6854_CR95","doi-asserted-by":"publisher","unstructured":"Beltran J, Guindel C, Moreno FM, Cruzado D, Garcia F, Arturo DLE (2018) Birdnet: a 3d object detection framework from lidar information. 2018 21st International conference on intelligent transportation systems (ITSC). https:\/\/doi.org\/10.1109\/ITSC.2018.8569311","DOI":"10.1109\/ITSC.2018.8569311"},{"key":"6854_CR96","doi-asserted-by":"publisher","unstructured":"Girshick R (2015) Fast r-cnn. 2015 IEEE Int Conf Comput Vis (ICCV). https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"6854_CR97","doi-asserted-by":"publisher","unstructured":"Barrera A, Guindel C, Beltr\u00e1n J, Garc\u00eda F (2020) Birdnet+: End-to-end 3d object detection in lidar bird\u2019s eye view. 2020 IEEE 23rd International conference on intelligent transportation systems (ITSC). https:\/\/doi.org\/10.1109\/ITSC45102.2020.9294293","DOI":"10.1109\/ITSC45102.2020.9294293"},{"key":"6854_CR98","doi-asserted-by":"publisher","unstructured":"Ali W, Abdelkarim S, Zidan M, Zahran M, Sallab AE (2019) Yolo3d: End-to-end real-time 3d oriented object bounding box detection from lidar point cloud. Comput Vis \u2013 ECCV 2018 Workshops, pp 716\u2013728. https:\/\/doi.org\/10.1007\/978-3-030-11015-4_54","DOI":"10.1007\/978-3-030-11015-4_54"},{"key":"6854_CR99","doi-asserted-by":"publisher","unstructured":"Redmon J, Farhadi A (2017) Yolo9000: Better, faster, stronger. 2017 IEEE Conference on computer vision and pattern recognition (CVPR), pp 6517\u20136525. https:\/\/doi.org\/10.1109\/CVPR.2017.690","DOI":"10.1109\/CVPR.2017.690"},{"key":"6854_CR100","doi-asserted-by":"publisher","unstructured":"Simon M, Milz S, Amende K, Gross HM (2018) Complex-yolo: Real-time 3d object detection on point clouds. Comput Vis \u2013 ECCV 2018 Workshops. https:\/\/doi.org\/10.48550\/arXiv.1803.06199","DOI":"10.48550\/arXiv.1803.06199"},{"key":"6854_CR101","doi-asserted-by":"publisher","unstructured":"Simon M, Amende K, Kraus A, Honer J, Samann T, Kaulbersch H, Milz S, Gross H-M (2019) Complexer-yolo: Real-time 3d object detection and tracking on semantic point clouds. 2019 IEEE\/CVF Conference on computer vision and pattern recognition workshops (CVPRW), pp 1190\u20131199. https:\/\/doi.org\/10.1109\/CVPRW.2019.00158","DOI":"10.1109\/CVPRW.2019.00158"},{"key":"6854_CR102","unstructured":"Yang B, Liang M, Urtasun R (2018) Hdnet: Exploiting hd maps for 3d object detection. ArXiv. abs\/2012.11704"},{"key":"6854_CR103","doi-asserted-by":"publisher","unstructured":"Huang Y, Zhou J, Li X, Dong Z, Xiao J, Wang S, Zhang H (2023) Menet: Map-enhanced 3d object detection in bird\u2019s-eye view for lidar point clouds. Int J Appl Earth Obs Geoinformation. 120:103337. https:\/\/doi.org\/10.1016\/j.jag.2023.103337","DOI":"10.1016\/j.jag.2023.103337"},{"key":"6854_CR104","doi-asserted-by":"publisher","unstructured":"Chen Y, Cai G, Xia Q, Liu Z, Zeng B, Zhang Z, Li J, Wang Z (2024) Epdet: Enhancing point clouds features with effective representation for 3d object detection. Int J Appl Earth Obs Geoinformation 127:103688. https:\/\/doi.org\/10.1016\/j.jag.2024.103688","DOI":"10.1016\/j.jag.2024.103688"},{"key":"6854_CR105","doi-asserted-by":"publisher","unstructured":"Chen Y, Li Y, Zhang X, Sun J, Jia J (2022) Focal sparse convolutional networks for 3d object detection. 2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 5418\u20135427. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00535","DOI":"10.1109\/CVPR52688.2022.00535"},{"key":"6854_CR106","doi-asserted-by":"publisher","unstructured":"Duta IC, Liu L, Zhu F, Shao L (2020) Pyramidal convolution: Rethinking convolutional neural networks for visual recognition. ArXiv. abs\/2006.11538. https:\/\/doi.org\/10.48550\/arXiv.2006.11538","DOI":"10.48550\/arXiv.2006.11538"},{"key":"6854_CR107","doi-asserted-by":"publisher","unstructured":"Ye M, Xu S, Cao T (2020) Hvnet: Hybrid voxel network for lidar based 3d object detection. 2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00170","DOI":"10.1109\/CVPR42600.2020.00170"},{"key":"6854_CR108","doi-asserted-by":"publisher","unstructured":"Duan K, Bai S, Xie L, Qi H, Huang Q, Tian Q (2019) Centernet: Keypoint triplets for object detection. 2019 IEEE\/CVF International conference on computer vision (ICCV), pp 6568\u20136577. https:\/\/doi.org\/10.1109\/ICCV.2019.00667","DOI":"10.1109\/ICCV.2019.00667"},{"key":"6854_CR109","doi-asserted-by":"publisher","unstructured":"Yin T, Zhou X, Krahenbuhl P (2021) Center-based 3d object detection and tracking. 2021 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 11779\u201311788. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01161","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"6854_CR110","doi-asserted-by":"publisher","unstructured":"Lang AH, Vora S, Caesar H, Zhou L, Beijbom O (2019) Pointpillars: Fast encoders for object detection from point clouds. 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/CVPR.2019.01298","DOI":"10.1109\/CVPR.2019.01298"},{"key":"6854_CR111","doi-asserted-by":"publisher","unstructured":"Deng J, Shi S, Li P-C, Zhou W-g, Zhang Y, Li H (2020) Voxel r-cnn: Towards high performance voxel-based 3d object detection. ArXiv. abs\/2012.15712, https:\/\/doi.org\/10.48550\/arXiv.2012.15712","DOI":"10.48550\/arXiv.2012.15712"},{"key":"6854_CR112","doi-asserted-by":"publisher","unstructured":"Engelcke M, Rao D, Wang DZ, Tong CH, Posner I (2016) Vote3deep: Fast object detection in 3d point clouds using efficient convolutional neural networks. 2017 IEEE International conference on robotics and automation (ICRA), pp 1355\u20131361. https:\/\/doi.org\/10.1109\/ICRA.2017.7989161","DOI":"10.1109\/ICRA.2017.7989161"},{"key":"6854_CR113","doi-asserted-by":"publisher","unstructured":"Yan Y, Mao Y, Li B (2018) Second: Sparsely embedded convolutional detection. Sensors 18(10):3337. https:\/\/doi.org\/10.3390\/s18103337","DOI":"10.3390\/s18103337"},{"key":"6854_CR114","doi-asserted-by":"publisher","unstructured":"Messikommer N, Gehrig D, Loquercio A, Scaramuzza D (2020) Event-based asynchronous sparse convolutional networks. Comput Vis \u2013 ECCV 2020, pp 415\u2013431. https:\/\/doi.org\/10.1007\/978-3-030-58598-3_25","DOI":"10.1007\/978-3-030-58598-3_25"},{"key":"6854_CR115","doi-asserted-by":"publisher","unstructured":"Li B, Chen J, Li X, Xu R, Li Q, Cao Y, Wu J, Qu L, Li Y, Diniz PSR (2024) Vfl3d: A single-stage fine-grained lightweight point cloud 3d object detection algorithm based on voxels. IEEE Trans Intell Transp Syst https:\/\/doi.org\/10.1109\/TITS.2024.3373227","DOI":"10.1109\/TITS.2024.3373227"},{"key":"6854_CR116","doi-asserted-by":"publisher","unstructured":"Chen Y, Liu J, Zhang X, Qi X, Jia J (2023) Voxelnext: Fully sparse voxelnet for 3d object detection and tracking. 2023 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 21674\u201321683. https:\/\/doi.org\/10.1109\/CVPR52729.2023.02076","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"6854_CR117","doi-asserted-by":"publisher","unstructured":"Zhang G, Chen J, Gao G, Li J, Liu S, Hu X (2024) Safdnet: A simple and effective network for fully sparse 3d object detection. ArXiv. abs\/2403.05817. https:\/\/doi.org\/10.48550\/arXiv.2403.05817","DOI":"10.48550\/arXiv.2403.05817"},{"key":"6854_CR118","doi-asserted-by":"publisher","unstructured":"He C, Li R, Li S, Zhang L (2022) Voxel set transformer: A set-to-set approach to 3d object detection from point clouds. 2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 8407\u20138417. https:\/\/doi.org\/10.48550\/arXiv.2203.10314","DOI":"10.48550\/arXiv.2203.10314"},{"key":"6854_CR119","doi-asserted-by":"publisher","unstructured":"Wang H, Shi C, Shi S, Lei M, Wang S, He D, Schiele B, Wang L (2023) Dsvt: Dynamic sparse voxel transformer with rotated sets. 2023 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.48550\/arXiv.2301.06051","DOI":"10.48550\/arXiv.2301.06051"},{"key":"6854_CR120","doi-asserted-by":"publisher","unstructured":"Li J, Dong S, Ding L, Xu T (2023) Mssvt++: Mixed-scale sparse voxel transformer with center voting for 3d object detection. IEEE Trans Pattern Anal Mach Intell pp 1\u201317. https:\/\/doi.org\/10.1109\/TPAMI.2023.3345880","DOI":"10.1109\/TPAMI.2023.3345880"},{"key":"6854_CR121","doi-asserted-by":"publisher","unstructured":"Li J-Y, Luo C, Yang X (2023) Pillarnext: Rethinking network designs for 3d object detection in lidar point clouds. 2023 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 17567\u201317576. https:\/\/doi.org\/10.1109\/CVPR52729.2023.01685","DOI":"10.1109\/CVPR52729.2023.01685"},{"key":"6854_CR122","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. 2016 IEEE Conference on computer vision and pattern recognition (CVPR), pp 770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"6854_CR123","doi-asserted-by":"publisher","unstructured":"Wang C, Liu Z (2023) Cafi-pillars: Infusing geometry priors for pillar-based 3d detectors through centroid-aware feature interaction. IEEE Trans Intell Veh pp 1\u201310. https:\/\/doi.org\/10.1109\/TIV.2023.3323377","DOI":"10.1109\/TIV.2023.3323377"},{"key":"6854_CR124","doi-asserted-by":"publisher","unstructured":"Shi S, Wang X, Li H (2018) Pointrcnn: 3d object proposal generation and detection from point cloud. 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 770\u2013779. https:\/\/doi.org\/10.48550\/arXiv.1812.04244","DOI":"10.48550\/arXiv.1812.04244"},{"key":"6854_CR125","doi-asserted-by":"publisher","unstructured":"Liu D, Wang Z (2023) Pointrcnn++: Towards more accurate two-stage 3d object detection from point cloud. 2023 China Automation Congress (CAC), pp 3099\u20133104. https:\/\/doi.org\/10.1109\/CAC59555.2023.10451778","DOI":"10.1109\/CAC59555.2023.10451778"},{"key":"6854_CR126","doi-asserted-by":"publisher","unstructured":"Yang Z, Sun Y, Liu S, Jia J (2020) 3dssd: Point-based 3d single stage object detector. 2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 11037\u201311045. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01105","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"6854_CR127","doi-asserted-by":"publisher","unstructured":"Chen C, Chen Z, Zhang J, Tao D (2022) Sasa: Semantics-augmented set abstraction for point-based 3d object detection. AAAI Conf Artif Intell. https:\/\/doi.org\/10.1609\/aaai.v36i1.19897","DOI":"10.1609\/aaai.v36i1.19897"},{"key":"6854_CR128","doi-asserted-by":"publisher","unstructured":"Zhang Y, Hu Q, Xu G, Ma Y, Wan J-H, Guo Y (2022) Not all points are equal: Learning highly efficient point-based detectors for 3d lidar point clouds. 2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 18931\u201318940. https:\/\/doi.org\/10.48550\/arXiv.2203.11139","DOI":"10.48550\/arXiv.2203.11139"},{"key":"6854_CR129","doi-asserted-by":"publisher","unstructured":"Chen Y, Cai G, Xia Q, Liu Z, Zeng B, Zhang Z, Su J, Wang Z (2024) Not all points are balanced: Class balanced single-stage outdoor multi-class 3d object detector from point clouds. Int J Appl Earth Obs Geoinformation 128:103766. https:\/\/doi.org\/10.1016\/j.jag.2024.103766","DOI":"10.1016\/j.jag.2024.103766"},{"key":"6854_CR130","doi-asserted-by":"publisher","unstructured":"Li X, Wang C, Zeng Z (2024) Ws-ssd: Achieving faster 3d object detection for autonomous driving via weighted point cloud sampling. Expert Syst Appl 249:123805. https:\/\/doi.org\/10.1016\/j.eswa.2024.123805","DOI":"10.1016\/j.eswa.2024.123805"},{"key":"6854_CR131","doi-asserted-by":"publisher","unstructured":"Shi W, Rajkumar R (2020) Point-gnn: Graph neural network for 3d object detection in a point cloud. 2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 1708\u20131716. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00178","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"6854_CR132","doi-asserted-by":"publisher","unstructured":"He Q, Wang Z, Zeng H, Zeng Y, Liu S, Zeng B (2020) Svga-net: Sparse voxel-graph attention network for 3d object detection from point clouds. AAAI Conf Artif Intell. https:\/\/doi.org\/10.48550\/arXiv.2006.04043","DOI":"10.48550\/arXiv.2006.04043"},{"issue":"5","key":"6854_CR133","doi-asserted-by":"publisher","first-page":"1458","DOI":"10.3390\/s24051458","volume":"24","author":"Z Liang","year":"2024","unstructured":"Liang Z, Huang Y, Bai Y (2024) Pre-segmented down-sampling accelerates graph neural network-based 3d object detection in autonomous driving. Sensors 24(5):1458. https:\/\/doi.org\/10.3390\/s24051458","journal-title":"Sensors"},{"key":"6854_CR134","doi-asserted-by":"publisher","unstructured":"Pan X, Xia Z, Song S, Li LE, Huang G (2020) 3d object detection with pointformer. 2021 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 7459\u20137468. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00738","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"6854_CR135","doi-asserted-by":"publisher","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. Comput Vis \u2013 ECCV 2020:213\u2013229. https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"6854_CR136","doi-asserted-by":"publisher","unstructured":"Misra I, Girdhar R, Joulin A (2021) An end-to-end transformer model for 3d object detection. 2021 IEEE\/CVF International conference on computer vision (ICCV), pp 2886\u20132897. https:\/\/doi.org\/10.48550\/arXiv.2109.08141","DOI":"10.48550\/arXiv.2109.08141"},{"key":"6854_CR137","doi-asserted-by":"publisher","unstructured":"Liu H, Ma Y, Wang H, Zhang C, Guo Y (2023) Anchorpoint: query design for transformer-based 3d object detection and tracking. IEEE Trans Intell Trans Syst, pp 10988-11000. https:\/\/doi.org\/10.1109\/TITS.2023.3282204","DOI":"10.1109\/TITS.2023.3282204"},{"key":"6854_CR138","doi-asserted-by":"publisher","unstructured":"Wang CX, Deng JC, He JF, Zhang TZ, Zhang Z, Zhang YD (2023) Long-short range adaptive transformer with dynamic sampling for 3d object detection. IEEE Transactions on Circuits and Systems for Video Technology, pp 7616\u20137629. https:\/\/doi.org\/10.1109\/tcsvt.2023.3272734","DOI":"10.1109\/tcsvt.2023.3272734"},{"key":"6854_CR139","doi-asserted-by":"publisher","unstructured":"Liu Z, Yang X, Tang H, Yang S, Han S (2023) Flatformer: Flattened window attention for efficient point cloud transformer. 2023 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 1200\u20131211. https:\/\/doi.org\/10.1109\/CVPR52729.2023.00122","DOI":"10.1109\/CVPR52729.2023.00122"},{"key":"6854_CR140","doi-asserted-by":"publisher","unstructured":"Zheng Y, Duan Y, Lu J, Zhou J, Tian Q (2022) Hyperdet3d: Learning a scene-conditioned 3d object detector. 2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.48550\/arXiv.2204.05599","DOI":"10.48550\/arXiv.2204.05599"},{"key":"6854_CR141","doi-asserted-by":"publisher","unstructured":"Shi S, Guo C, Jiang L, Wang Z, Shi J, Wang X, Li H (2019) Pv-rcnn: Point-voxel feature set abstraction for 3d object detection. 2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.48550\/arXiv.1912.13192","DOI":"10.48550\/arXiv.1912.13192"},{"key":"6854_CR142","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/s11263-022-01710-9","volume":"131","author":"S Shi","year":"2021","unstructured":"Shi S, Jiang L, Deng J, Wang Z, Guo C, Shi J, Wang X, Li H (2021) Pv-rcnn++: Point-voxel feature set abstraction with local vector representation for 3d object detection. Int J Comput Vis 131:531\u2013551. https:\/\/doi.org\/10.1007\/s11263-022-01710-9","journal-title":"Int J Comput Vis"},{"key":"6854_CR143","doi-asserted-by":"publisher","unstructured":"Noh J, Lee S, Ham B (2021) Hvpr: Hybrid voxel-point representation for single-stage 3d object detection. Computer Vision and Pattern Recognition, pp 14600\u201314609. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01437","DOI":"10.1109\/CVPR46437.2021.01437"},{"key":"6854_CR144","doi-asserted-by":"publisher","first-page":"14894","DOI":"10.1109\/JSEN.2024.3380898","volume":"24","author":"P Deng","year":"2024","unstructured":"Deng P, Zhou L, Chen J (2024) Pvc-ssd: Point-voxel dual-channel fusion with cascade point estimation for anchor-free single-stage 3-d object detection. IEEE Sens J 24:14894\u201314904. https:\/\/doi.org\/10.1109\/JSEN.2024.3380898","journal-title":"IEEE Sens J"},{"issue":"11","key":"6854_CR145","doi-asserted-by":"publisher","first-page":"2213","DOI":"10.3390\/electronics13112213","volume":"13","author":"Z Zhang","year":"2024","unstructured":"Zhang Z, Zhu Z, Bai Y, Jin Y, Wang M (2024) Multi-scale feature fusion point cloud object detection based on original point cloud and projection. Electronics 13(11):2213. https:\/\/doi.org\/10.3390\/electronics13112213","journal-title":"Electronics"},{"key":"6854_CR146","doi-asserted-by":"publisher","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. 2021 IEEE\/CVF International conference on computer vision (ICCV), pp 9992\u201310002. https:\/\/doi.org\/10.48550\/arXiv.2103.14030","DOI":"10.48550\/arXiv.2103.14030"},{"key":"6854_CR147","doi-asserted-by":"publisher","unstructured":"Shao Y, Tan A, Sun Z, Zheng E, Yan T, Liao P (2024) Pv-ssd: A multi-modal point cloud 3d object detector based on projection features and voxel features. IEEE Trans Emerg Top Comput Intell pp 1\u201314. https:\/\/doi.org\/10.1109\/TETCI.2024.3389710","DOI":"10.1109\/TETCI.2024.3389710"},{"key":"6854_CR148","doi-asserted-by":"publisher","unstructured":"Wang HJ, Chen XY, Yuan QB, Liu P (2024) A review of 3d object detection based on autonomous driving. Visual Computer. https:\/\/doi.org\/10.1007\/s00371-024-03480-6. Wang, Huijuan Chen, Xinyue Yuan, Quanbo Liu, Peng 1432-2315","DOI":"10.1007\/s00371-024-03480-6"},{"key":"6854_CR149","doi-asserted-by":"publisher","unstructured":"Qi C, Liu W, Wu C, Su H, Guibas LJ (2017) Frustum pointnets for 3d object detection from rgb-d data. 2018 IEEE\/CVF Conference on computer vision and pattern recognition, pp 918\u2013927. https:\/\/doi.org\/10.1109\/CVPR.2018.00102","DOI":"10.1109\/CVPR.2018.00102"},{"key":"6854_CR150","doi-asserted-by":"publisher","unstructured":"Wang Z, Jia K (2019) Frustum convnet: Sliding frustums to aggregate local point-wise features for amodal. 2019 IEEE\/RSJ International conference on intelligent robots and systems (IROS), pp 1742\u20131749. https:\/\/doi.org\/10.1109\/IROS40897.2019.8968513","DOI":"10.1109\/IROS40897.2019.8968513"},{"key":"6854_CR151","doi-asserted-by":"publisher","unstructured":"Vora S, Lang A, Helou B, Beijbom O (2019) Pointpainting: Sequential fusion for 3d object detection. 2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.48550\/arXiv.1911.10150","DOI":"10.48550\/arXiv.1911.10150"},{"key":"6854_CR152","unstructured":"Yin T, Zhou X, Kr\u00e4henb\u00fchl P (2021) Multimodal virtual point 3d detection. Neural Inform Process Syst"},{"key":"6854_CR153","doi-asserted-by":"publisher","unstructured":"Chen X, Ma H, Wan J, Li B, Xia T (2017) Multi-view 3d object detection network for autonomous driving. 2017 IEEE Conference on computer vision and pattern recognition (CVPR), pp 6526\u20136534. https:\/\/doi.org\/10.1109\/CVPR.2017.691","DOI":"10.1109\/CVPR.2017.691"},{"key":"6854_CR154","doi-asserted-by":"publisher","unstructured":"Ku J, Mozifian M, Lee J, Harakeh A, Waslander S (2017) Joint 3d proposal generation and object detection from view aggregation. 2018 IEEE\/RSJ International conference on intelligent robots and systems (IROS). https:\/\/doi.org\/10.1109\/IROS.2018.8594049","DOI":"10.1109\/IROS.2018.8594049"},{"key":"6854_CR155","doi-asserted-by":"crossref","unstructured":"Bai X, Hu Z, Zhu X, Huang Q, Chen Y, Fu H, Tai C-L (2022) Transfusion: Robust lidar-camera fusion for 3d object detection with transformers. 2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 1080\u20131089","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"6854_CR156","doi-asserted-by":"crossref","unstructured":"Philion J, Fidler S (2020) Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D. arXiv:2008.05711","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"6854_CR157","doi-asserted-by":"crossref","unstructured":"Liu Z, Tang H, Amini A, Yang X, Mao H, Rus D, Han S (2024) BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird\u2019s-Eye View Representation. arXiv:2205.13542","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"6854_CR158","doi-asserted-by":"publisher","unstructured":"Huang T, Liu Z, Chen X, Bai X (2020) Epnet: Enhancing point features with image semantics for 3d object detection. Comput Vis \u2013 ECCV 2020, pp 35\u201352. https:\/\/doi.org\/10.1007\/978-3-030-58555-6_3","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"6854_CR159","doi-asserted-by":"publisher","unstructured":"Liu Z, Huang T, Li B, Chen X, Wang X, Bai X (2021) Epnet++: Cascade bi-directional fusion for multi-modal 3d object detection. IEEE Trans Pattern Anal Mach Intell 45:8324\u20138341. https:\/\/doi.org\/10.48550\/arXiv.2112.11088","DOI":"10.48550\/arXiv.2112.11088"},{"key":"6854_CR160","doi-asserted-by":"publisher","unstructured":"Cao F, Xue J, Tao C, Luo X, Gao Z, Zhang Z, Zheng S, Zhu Y (2023) Mchformer: A multi-cross hybrid former of point-image for 3d object detection. IEEE Trans Intell Veh pp 1\u201312. https:\/\/doi.org\/10.1109\/TIV.2023.3323518","DOI":"10.1109\/TIV.2023.3323518"},{"key":"6854_CR161","doi-asserted-by":"publisher","unstructured":"Xie Y, Xu C, Rakotosaona M-J, Rim P, Tombari F, Keutzer K, Tomizuka M, Zhan W (2023) Sparsefusion: Fusing multi-modal sparse representations for multi-sensor 3d object detection. 2023 IEEE\/CVF International conference on computer vision (ICCV), pp 17545\u201317556. https:\/\/doi.org\/10.1109\/ICCV51070.2023.01613","DOI":"10.1109\/ICCV51070.2023.01613"},{"key":"6854_CR162","doi-asserted-by":"crossref","unstructured":"Yin J, Shen J, Chen R, Li W, Yang R, Frossard P, Wang W (2024) IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection. arXiv:2403.15241","DOI":"10.1109\/CVPR52733.2024.01412"},{"key":"6854_CR163","doi-asserted-by":"publisher","unstructured":"Yan J, Yingfei L, Sun J, Jia F, Li S, Wang T, Zhang X (2023) Cross modal transformer: Towards fast and robust 3d object detection. 2023 IEEE\/CVF International conference on computer vision (ICCV), pp 18222\u201318232. https:\/\/doi.org\/10.1109\/ICCV51070.2023.01675","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"6854_CR164","doi-asserted-by":"publisher","unstructured":"Xie G, Chen Z, Gao M, Hu M, Qin X (2024) Ppf-det: Point-pixel fusion for multi-modal 3d object detection. IEEE Trans Intell Trans Syst pp 1\u201314. https:\/\/doi.org\/10.1109\/TITS.2023.3347078","DOI":"10.1109\/TITS.2023.3347078"},{"key":"6854_CR165","doi-asserted-by":"publisher","unstructured":"Song Z, Wei H, Bai L, Yang L, Jia C (2023) Graphalign: Enhancing accurate feature alignment by graph matching for multi-modal 3d object detection. 2023 IEEE\/CVF International conference on computer vision (ICCV), pp 3335\u20133346. https:\/\/doi.org\/10.1109\/ICCV51070.2023.00311","DOI":"10.1109\/ICCV51070.2023.00311"},{"key":"6854_CR166","unstructured":"Hu H, Wang F, Su J, Wang Y, Hu L, Fang W, Xu J, Zhang Z (2023) EA-LSS: Edge-aware Lift-splat-shot Framework for 3D BEV Object Detection. arXiv:2303.17895"},{"key":"6854_CR167","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.cag.2017.11.010","volume":"71","author":"A Boulch","year":"2018","unstructured":"Boulch A, Guerry J, Le Saux B, Audebert N (2018) Snapnet: 3d point cloud semantic labeling with 2d deep segmentation networks. Comput Graph 71:189\u2013198. https:\/\/doi.org\/10.1016\/j.cag.2017.11.010","journal-title":"Comput Graph"},{"key":"6854_CR168","doi-asserted-by":"publisher","unstructured":"Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) Squeezenet: Alexnet-level accuracy with 50x fewer parameters and \u00a10.5mb model size. arXiv.org. https:\/\/doi.org\/10.48550\/arXiv.1602.07360","DOI":"10.48550\/arXiv.1602.07360"},{"key":"6854_CR169","doi-asserted-by":"publisher","unstructured":"Wu B, Wan A, Yue X, Keutzer K (2017) Squeezeseg: Convolutional neural nets with recurrent crf for real-time road-object segmentation from 3d lidar point cloud. https:\/\/doi.org\/10.1109\/ICRA.2018.8462926","DOI":"10.1109\/ICRA.2018.8462926"},{"key":"6854_CR170","doi-asserted-by":"publisher","unstructured":"Wu B, Zhou X, Zhao S, Yue X, Keutzer K (2018) Squeezesegv2: Improved model structure and unsupervised domain adaptation for road-object segmentation from a lidar point cloud. 2019 International conference on robotics and automation (ICRA), pp 4376\u20134382. https:\/\/doi.org\/10.1109\/ICRA.2019.8793495","DOI":"10.1109\/ICRA.2019.8793495"},{"key":"6854_CR171","doi-asserted-by":"publisher","unstructured":"Xu C, Wu B, Wang Z, Zhan W, Vajda P, Keutzer K, Tomizuka M (2020) Squeezesegv3: Spatially-adaptive convolution for efficient point-cloud segmentation. Comput Vis \u2013 ECCV 2020, pp 1\u201319. https:\/\/doi.org\/10.1007\/978-3-030-58604-1_1","DOI":"10.1007\/978-3-030-58604-1_1"},{"key":"6854_CR172","doi-asserted-by":"publisher","unstructured":"Milioto A, Vizzo I, Behley J, Stachniss C (2019) Rangenet ++: Fast and accurate lidar semantic segmentation. 2019 IEEE\/RSJ International conference on intelligent robots and systems (IROS), pp 4213\u20134220. https:\/\/doi.org\/10.1109\/IROS40897.2019.8967762","DOI":"10.1109\/IROS40897.2019.8967762"},{"key":"6854_CR173","doi-asserted-by":"publisher","unstructured":"Aksoy E, Baci S, Cavdar S (2020) Salsanet: Fast road and vehicle segmentation in lidar point clouds for autonomous driving. 2020 IEEE Intelligent vehicles symposium (IV), pp 926\u2013932. https:\/\/doi.org\/10.1109\/IV47402.2020.9304694","DOI":"10.1109\/IV47402.2020.9304694"},{"key":"6854_CR174","doi-asserted-by":"publisher","unstructured":"Cortinhal T, Tzelepis G, Erdal\u00a0Aksoy E (2020) Salsanext: Fast, uncertainty-aware semantic segmentation of lidar point clouds. Adv Vis Comput pp 207\u2013222. https:\/\/doi.org\/10.1007\/978-3-030-64559-5_16","DOI":"10.1007\/978-3-030-64559-5_16"},{"key":"6854_CR175","doi-asserted-by":"publisher","unstructured":"Cheng H, Han X, Xiao G (2022) Cenet: Toward concise and efficient lidar semantic segmentation for autonomous driving. 2022 IEEE International conference on multimedia and expo (ICME), pp 01\u201306. https:\/\/doi.org\/10.1109\/ICME52920.2022.9859693","DOI":"10.1109\/ICME52920.2022.9859693"},{"key":"6854_CR176","doi-asserted-by":"publisher","unstructured":"Kong L, Liu Y, Runnan C, Ma B, Zhu X, Li Y, Hou Y, Qiao Y, Liu Z (2023) Rethinking range view representation for lidar segmentation. IEEE Int Conf Comput Vis pp 228\u2013240. https:\/\/doi.org\/10.1109\/ICCV51070.2023.00028","DOI":"10.1109\/ICCV51070.2023.00028"},{"issue":"8","key":"6854_CR177","doi-asserted-by":"publisher","first-page":"5155","DOI":"10.1007\/s00371-023-02907-w","volume":"40","author":"D Ren","year":"2024","unstructured":"Ren D, Li J, Wu Z, Guo J, Wei M, Guo Y (2024) Mffnet: multimodal feature fusion network for point cloud semantic segmentation. Vis Comput 40(8):5155\u20135167. https:\/\/doi.org\/10.1007\/s00371-023-02907-w","journal-title":"Vis Comput"},{"key":"6854_CR178","doi-asserted-by":"publisher","unstructured":"Huang J, You S (2016) Point cloud labeling using 3d convolutional neural network. 2016 23rd International conference on pattern recognition (ICPR), pp 2670\u20132675. https:\/\/doi.org\/10.1109\/ICPR.2016.7900038","DOI":"10.1109\/ICPR.2016.7900038"},{"key":"6854_CR179","doi-asserted-by":"publisher","unstructured":"Tchapmi L, Choy C, Armeni I, Gwak J, Savarese S (2017) Segcloud: Semantic segmentation of 3d point clouds. 2017 International conference on 3d vision (3DV), pp 537\u2013547. https:\/\/doi.org\/10.1109\/3DV.2017.00067","DOI":"10.1109\/3DV.2017.00067"},{"key":"6854_CR180","doi-asserted-by":"crossref","unstructured":"Rethage D, Wald J, Sturm J, Navab N, Tombari F (2018) Fully-convolutional point networks for large-scale point clouds. ComputVis \u2013 ECCV 2018:625\u2013640","DOI":"10.1007\/978-3-030-01225-0_37"},{"key":"6854_CR181","doi-asserted-by":"publisher","unstructured":"Zhou H, Zhu X, Song X, Ma Y, Wang Z, Li H, Lin D (2020) Cylinder3d: An effective 3d framework for driving-scene lidar semantic segmentation. ArXiv. abs\/2008.01550, https:\/\/doi.org\/10.48550\/arXiv.2008.01550","DOI":"10.48550\/arXiv.2008.01550"},{"key":"6854_CR182","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01520","author":"Z Hu","year":"2021","unstructured":"Hu Z, Bai X, Shang J, Zhang R, Dong J, Wang X, Sun G, Fu H, Tai C-L (2021) Vmnet: Voxel-mesh network for geodesic-aware 3d semantic segmentation. IEEE Int Conf Comput Vis. https:\/\/doi.org\/10.1109\/ICCV48922.2021.01520","journal-title":"IEEE Int Conf Comput Vis"},{"key":"6854_CR183","doi-asserted-by":"publisher","unstructured":"Ye M, Xu S, Cao T, Chen Q (2021) Drinet: A dual-representation iterative learning network for point cloud segmentation. 2021 IEEE\/CVF International conference on computer vision (ICCV), 7427\u20137436. https:\/\/doi.org\/10.48550\/arXiv.2108.04023","DOI":"10.48550\/arXiv.2108.04023"},{"key":"6854_CR184","doi-asserted-by":"publisher","unstructured":"Ye M, Wan R, Xu S, Cao T, Chen Q (2021) Drinet++: Efficient voxel-as-point point cloud segmentation. ArXiv. abs\/2111.08318, https:\/\/doi.org\/10.48550\/arXiv.2111.08318","DOI":"10.48550\/arXiv.2111.08318"},{"key":"6854_CR185","doi-asserted-by":"publisher","unstructured":"Unal O, Dai D, Gool LV (2022) Scribble-supervised lidar semantic segmentation. 2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 2687\u20132697. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00272","DOI":"10.1109\/CVPR52688.2022.00272"},{"key":"6854_CR186","doi-asserted-by":"publisher","unstructured":"Li L, Shum HPH, Breckon T (2023) Less is more: Reducing task and model complexity for 3d point cloud semantic segmentation. 2023 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.48550\/arXiv.2303.11203","DOI":"10.48550\/arXiv.2303.11203"},{"key":"6854_CR187","doi-asserted-by":"publisher","unstructured":"Jiang M, Wu Y, Zhao Z, Lu C (2018) Pointsift: A sift-like network module for 3d point cloud semantic segmentation. ArXiv. abs\/1807.00652. https:\/\/doi.org\/10.48550\/arXiv.1807.00652","DOI":"10.48550\/arXiv.1807.00652"},{"key":"6854_CR188","doi-asserted-by":"publisher","unstructured":"Hu Q, Yang B, Xie L, Rosa S, Guo Y, Wang Z, Trigoni A, Markham A (2019) Randla-net: Efficient semantic segmentation of large-scale point clouds. 2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 11105\u201311114. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01112","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"6854_CR189","doi-asserted-by":"publisher","unstructured":"Fan S, Dong Q, Zhu F, Lv Y, Ye P, Wang FY (2021) Scf-net: Learning spatial contextual features for large-scale point cloud segmentation. 2021 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), 14499\u201314508. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01427","DOI":"10.1109\/CVPR46437.2021.01427"},{"key":"6854_CR190","doi-asserted-by":"publisher","unstructured":"Qiu S, Anwar S, Barnes N (2021) Semantic segmentation for real point cloud scenes via bilateral augmentation and adaptive fusion. 2021 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), 1757\u20131767. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00180","DOI":"10.1109\/CVPR46437.2021.00180"},{"key":"6854_CR191","doi-asserted-by":"publisher","unstructured":"Zhang Z, Hua BS, Yeung SK (2019) Shellnet: Efficient point cloud convolutional neural networks using concentric shells statistics. 2019 IEEE\/CVF International conference on computer vision (ICCV), pp 1607\u20131616. https:\/\/doi.org\/10.1109\/ICCV.2019.00169","DOI":"10.1109\/ICCV.2019.00169"},{"key":"6854_CR192","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2021.3107006","volume":"19","author":"K Yan","year":"2022","unstructured":"Yan K, Hu Q, Wang H, Huang X, Li L, Ji S (2022) Continuous mapping convolution for large-scale point clouds semantic segmentation. IEEE Geosci Remote Sens Lett 19:1\u20135. https:\/\/doi.org\/10.1109\/LGRS.2021.3107006","journal-title":"IEEE Geosci Remote Sens Lett"},{"issue":"1","key":"6854_CR193","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1109\/TCYB.2022.3159815","volume":"53","author":"K Liu","year":"2023","unstructured":"Liu K, Gao Z, Lin F, Chen BM (2023) Fg-net: A fast and accurate framework for large-scale lidar point cloud understanding. IEEE Trans Cybern 53(1):553\u2013564. https:\/\/doi.org\/10.1109\/TCYB.2022.3159815","journal-title":"IEEE Trans Cybern"},{"issue":"2","key":"6854_CR194","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/s00530-021-00770-0","volume":"28","author":"Y Fang","year":"2022","unstructured":"Fang Y, Xu C, Zhou C, Cui Z, Hu C (2022) Direction-induced convolution for point cloud analysis. Multimedia Syst 28(2):457\u2013468. https:\/\/doi.org\/10.1007\/s00530-021-00770-0","journal-title":"Multimedia Syst"},{"key":"6854_CR195","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3162582","volume":"60","author":"Y Li","year":"2022","unstructured":"Li Y, Li X, Zhang Z, Shuang F, Lin Q, Jiang J (2022) Densekpnet: Dense kernel point convolutional neural networks for point cloud semantic segmentation. IEEE Trans Geosci Remote Sens 60:1\u201313. https:\/\/doi.org\/10.1109\/TGRS.2022.3162582","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"6854_CR196","doi-asserted-by":"publisher","unstructured":"Ding X, Zhang X, Han J, Ding G (2022) Scaling up your kernels to 31\u00d731: Revisiting large kernel design in cnns. 2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), 11953\u201311965. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01166","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"6854_CR197","doi-asserted-by":"publisher","unstructured":"Chen H, Chu X, Ren Y, Zhao X, Huang K (2024) Pelk: Parameter-efficient large kernel convnets with peripheral convolution. ArXiv. abs\/2403.07589, https:\/\/doi.org\/10.48550\/arXiv.2403.07589","DOI":"10.48550\/arXiv.2403.07589"},{"issue":"5","key":"6854_CR198","doi-asserted-by":"publisher","first-page":"3833","DOI":"10.1007\/s40747-021-00618-0","volume":"8","author":"L Wang","year":"2022","unstructured":"Wang L, Wu J, Liu X, Ma X, Cheng J (2022) Semantic segmentation of large-scale point clouds based on dilated nearest neighbors graph. Complex Intell Syst 8(5):3833\u20133845. https:\/\/doi.org\/10.1007\/s40747-021-00618-0","journal-title":"Complex Intell Syst"},{"issue":"3","key":"6854_CR199","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1007\/s00371-021-02351-8","volume":"39","author":"L Chen","year":"2023","unstructured":"Chen L, Zhang Q (2023) Ddgcn: graph convolution network based on direction and distance for point cloud learning. Vis Comput 39(3):863\u2013873. https:\/\/doi.org\/10.1007\/s00371-021-02351-8","journal-title":"Vis Comput"},{"key":"6854_CR200","doi-asserted-by":"publisher","unstructured":"Yang F, Davoine F, Wang H, Jin Z (2022) Continuous conditional random field convolution for point cloud segmentation. Pattern Recogn 122:108357. https:\/\/doi.org\/10.1016\/j.patcog.2021.108357","DOI":"10.1016\/j.patcog.2021.108357"},{"key":"6854_CR201","doi-asserted-by":"publisher","unstructured":"Chen C, Fragonara LZ, Tsourdos A (2019) Gapnet: Graph attention based point neural network for exploiting local feature of point cloud. ArXiv. abs\/1905.08705, https:\/\/doi.org\/10.48550\/arXiv.1905.08705","DOI":"10.48550\/arXiv.1905.08705"},{"key":"6854_CR202","doi-asserted-by":"publisher","unstructured":"Wang L, Huang Y, Hou Y, Zhang S, Shan J (2019) Graph attention convolution for point cloud semantic segmentation. 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 10288\u201310297. https:\/\/doi.org\/10.1109\/CVPR.2019.01054","DOI":"10.1109\/CVPR.2019.01054"},{"issue":"4","key":"6854_CR203","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.3390\/rs14041036","volume":"14","author":"W Jing","year":"2022","unstructured":"Jing W, Zhang W, Li L, Di D, Chen G, Wang J (2022) Agnet: An attention-based graph network for point cloud classification and segmentation. Remote Sensing 14(4):1036. https:\/\/doi.org\/10.3390\/rs14041036","journal-title":"Remote Sensing"},{"key":"6854_CR204","doi-asserted-by":"publisher","first-page":"10459","DOI":"10.1109\/ACCESS.2023.3339657","volume":"12","author":"T Zheng","year":"2024","unstructured":"Zheng T, Chen J, Feng W, Yu C (2024) A graph aggregation convolution and attention mechanism based semantic segmentation method for sparse lidar point cloud data. IEEE Access 12:10459\u201310469. https:\/\/doi.org\/10.1109\/ACCESS.2023.3339657","journal-title":"IEEE Access"},{"key":"6854_CR205","doi-asserted-by":"publisher","first-page":"70550","DOI":"10.1109\/ACCESS.2024.3402327","volume":"12","author":"X Zhang","year":"2024","unstructured":"Zhang X, Feng L (2024) Edge enhancement oriented graph convolutional networks for point cloud segmentation. IEEE Access 12:70550\u201370558. https:\/\/doi.org\/10.1109\/ACCESS.2024.3402327","journal-title":"IEEE Access"},{"key":"6854_CR206","doi-asserted-by":"publisher","unstructured":"Wu X, Jiang L, Wang P-S, Liu Z, Liu X, Qiao Y, Ouyang W, He T, Zhao H (2023) Point transformer v3: Simpler, faster, stronger. ArXiv. abs\/2312.10035, https:\/\/doi.org\/10.48550\/arXiv.2312.10035","DOI":"10.48550\/arXiv.2312.10035"},{"key":"6854_CR207","doi-asserted-by":"publisher","unstructured":"Lai X, Liu J, Jiang L, Wang L, Zhao H, Liu S, Qi X, Jia J (2022) Stratified transformer for 3d point cloud segmentation. 2022 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 8490\u20138499. https:\/\/doi.org\/10.48550\/arXiv.2203.14508","DOI":"10.48550\/arXiv.2203.14508"},{"issue":"4","key":"6854_CR208","doi-asserted-by":"publisher","first-page":"3169","DOI":"10.1007\/s10489-024-05302-7","volume":"54","author":"M Li","year":"2024","unstructured":"Li M, Wang G, Zhu M, Li C, Liu H, Pan X, Long Q (2024) Dfamnet: dual fusion attention multi-modal network for semantic segmentation on lidar point clouds. Appl Intell 54(4):3169\u20133180. https:\/\/doi.org\/10.1007\/s10489-024-05302-7","journal-title":"Appl Intell"},{"key":"6854_CR209","doi-asserted-by":"publisher","unstructured":"Kolodiazhnyi M, Vorontsova A, Konushin A, Rukhovich DD (2023) Oneformer3d: One transformer for unified point cloud segmentation. ArXiv. abs\/2311.14405, https:\/\/doi.org\/10.48550\/arXiv.2311.14405","DOI":"10.48550\/arXiv.2311.14405"},{"key":"6854_CR210","doi-asserted-by":"publisher","unstructured":"Xu W, Shi C, Tu S, Zhou X, Liang D, Bai X (2024) A unified framework for 3d scene understanding. ArXiv. abs\/2407.03263, https:\/\/doi.org\/10.48550\/arXiv.2407.03263","DOI":"10.48550\/arXiv.2407.03263"},{"key":"6854_CR211","doi-asserted-by":"publisher","unstructured":"Tran AT, Le HS, Lee SH, Kwon KR (2024) Pointct: Point central transformer network for weakly-supervised point cloud semantic segmentation. 2024 IEEE\/CVF Winter conference on applications of computer vision (WACV), 3544\u20133553. https:\/\/doi.org\/10.1109\/WACV57701.2024.00352","DOI":"10.1109\/WACV57701.2024.00352"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06854-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06854-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06854-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T15:42:41Z","timestamp":1762530161000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06854-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,30]]},"references-count":211,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["6854"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06854-y","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,30]]},"assertion":[{"value":"29 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflicts of interest to report regarding the present study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}],"article-number":"991"}}