{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T18:23:22Z","timestamp":1772994202509,"version":"3.50.1"},"reference-count":32,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T00:00:00Z","timestamp":1747008000000},"content-version":"vor","delay-in-days":131,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100004867","name":"Chongqing University of Technology","doi-asserted-by":"publisher","award":["2021ZDZ003"],"award-info":[{"award-number":["2021ZDZ003"]}],"id":[{"id":"10.13039\/501100004867","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Computers &amp; Digital Techniques"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>The processing of point cloud data has become a significant area of research in the modern field of perception. Classification and segmentation are critical tasks in autonomous driving, environmental perception, and digital twins. Algorithms that directly extract features from raw point cloud data have simple architectures, but they are constrained by computational demands and limited efficiency. This makes effective deployment on resource\u2010limited devices challenging. This article introduces GRSNet, an ultra\u2010lightweight algorithm. The principal innovation is a new sampling method named golden ratio sampling (GRS), which generates sampling point indices directly using the golden ratio to subsequently locate the corresponding sampling points. This method efficiently extracts representative points from point cloud data and integrates them into deep networks. Leveraging GRS, this study combines the concepts from GhostNet and self\u2010attention mechanisms to develop a feature extraction module dubbed the SA_Ghost Block, forming the core of GRSNet. Comparative experiments with leading algorithms on established point cloud open\u2010source datasets demonstrate that GRSNet achieves superior performance, maintaining only 0.7\u2009M parameters.<\/jats:p>","DOI":"10.1049\/cdt2\/7934018","type":"journal-article","created":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T00:33:32Z","timestamp":1747096412000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GRSNet: An Ultra\u2010Lightweight Neural Network for 3D Point Cloud Classification and Segmentation"],"prefix":"10.1049","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4676-4545","authenticated-orcid":false,"given":"Zourong","family":"Long","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0920-7972","authenticated-orcid":false,"given":"Gen","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9830-0497","authenticated-orcid":false,"given":"You","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0469-6254","authenticated-orcid":false,"given":"Hong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6971-3443","authenticated-orcid":false,"given":"Chao","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"265","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"e_1_2_10_1_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3195555"},{"key":"e_1_2_10_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2021.07.003"},{"key":"e_1_2_10_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3086804"},{"key":"e_1_2_10_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108796"},{"key":"e_1_2_10_5_2","doi-asserted-by":"crossref","unstructured":"PrakashA. ChittaK. andGeigerA. Multi-Modal Fusion Transformer for End-to-End Autonomous Driving 2021.","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"e_1_2_10_6_2","doi-asserted-by":"crossref","unstructured":"LvD. YingX. CuiY. SongJ. QianK. andLiM. Research on the Technology of LIDAR Data Processing International Conference on Electronics Instrumentation Information Systems 2017 IEEE 1\u20135.","DOI":"10.1109\/EIIS.2017.8298694"},{"key":"e_1_2_10_7_2","doi-asserted-by":"crossref","unstructured":"QiC. SuH. MoK. andGuibasL. J. Pointnet: Deep Learning on Point Sets for 3d Classification and Segmentation 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016 IEEE 77\u201385.","DOI":"10.1109\/CVPR.2017.16"},{"key":"e_1_2_10_8_2","unstructured":"QiC. YiL. SuH. andGuibasL. J. Pointnet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space Neural Information Processing Systems 2017 ACM 5105\u20135114."},{"key":"e_1_2_10_9_2","doi-asserted-by":"crossref","unstructured":"RanH. LiuJ. andWangC. Surface Representation for Point Clouds 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022 IEEE 18920\u201318930.","DOI":"10.1109\/CVPR52688.2022.01837"},{"key":"e_1_2_10_10_2","unstructured":"MaX. QinC. YouH. RanH. andFuY. R. Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework 2022 ArXiv vol. abs\/2202.07123."},{"key":"e_1_2_10_11_2","doi-asserted-by":"crossref","unstructured":"UyM. A. PhamQ. H. HuaB. S. NguyenD. T. andYeungS. K. Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data 2019.","DOI":"10.1109\/ICCV.2019.00167"},{"key":"e_1_2_10_12_2","doi-asserted-by":"crossref","unstructured":"YangB. LuoW. andUrtasunR. Pixor: Real-Time 3d Object Detection from Point Clouds 2019 IEEE.","DOI":"10.1109\/CVPR.2018.00798"},{"key":"e_1_2_10_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3012692"},{"key":"e_1_2_10_14_2","doi-asserted-by":"crossref","unstructured":"SuH. MajiS. KalogerakisE. andLearned-MillerE. G. Multi-View Convolutional Neural Networks for 3D Shape Recognition Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2015 CVF 945\u2013953.","DOI":"10.1109\/ICCV.2015.114"},{"key":"e_1_2_10_15_2","doi-asserted-by":"publisher","DOI":"10.1002\/int.23073"},{"key":"e_1_2_10_16_2","doi-asserted-by":"crossref","unstructured":"MaturanaD.andSchererS. Voxnet: A 3d Convolutional Neural Network for Real-Time Object Recognition 2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) 2015 IEEE 922\u2013928.","DOI":"10.1109\/IROS.2015.7353481"},{"key":"e_1_2_10_17_2","doi-asserted-by":"crossref","unstructured":"ZhouY.andTuzelO. Voxelnet: End-to-End Learning for Point Cloud Based 3d Object Detection 2017.","DOI":"10.1109\/CVPR.2018.00472"},{"key":"e_1_2_10_18_2","doi-asserted-by":"crossref","unstructured":"RieglerG. UlusoyA. O. andGeigerA. OctNet: Learning Deep 3d Representations at High Resolutions 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017 CVF 3577\u20133586.","DOI":"10.1109\/CVPR.2017.701"},{"key":"e_1_2_10_19_2","doi-asserted-by":"crossref","unstructured":"ZhaoH. JiangL. JiaJ. TorrP. H. andKoltunV. Point Transformer Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) 2021 IEEE 16259\u201316268.","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"e_1_2_10_20_2","doi-asserted-by":"crossref","unstructured":"ZhangR. WangL. WangY. GaoP. LiH. andShiJ. Parameter Is Not All You Need: Starting From Non-Parametric Networks for 3d Point Cloud Analysis 2023 ArXiv vol. abs\/2303.08134.","DOI":"10.1109\/CVPR52729.2023.00517"},{"key":"e_1_2_10_21_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3326362","article-title":"Dynamic Graph CNN for Learning on Point Clouds","volume":"38","author":"Wang Y.","year":"2018","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_10_22_2","unstructured":"LinZ. LiuZ. WangY. ZhangL. andZhuC. Rcbevdet++: Toward High-Accuracy Radar-Camera Fusion 3d Perception Network 2024 ArXiv vol. abs\/2409.04979."},{"key":"e_1_2_10_23_2","doi-asserted-by":"crossref","unstructured":"ChenA. ZhangK. andZhangR. et al.Pimae: Point Cloud and Image Interactive Masked Autoencoders for 3d Object Detection 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023 IEEE 5291\u20135301.","DOI":"10.1109\/CVPR52729.2023.00512"},{"key":"e_1_2_10_24_2","doi-asserted-by":"crossref","unstructured":"XueL. GaoM. andXingC. et al.Ulip: Learning a Unified Representation of Language Images and Point Clouds for 3d Understanding 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022 IEEE 1179\u20131189.","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"e_1_2_10_25_2","doi-asserted-by":"crossref","unstructured":"XueL. YuN. andZhangS. et al.Ulip-2: Towards Scalable Multimodal Pre-Training for 3d Understanding 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023 IEEE 27081\u201327091.","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"e_1_2_10_26_2","doi-asserted-by":"crossref","unstructured":"QiZ. FangY. andSunZ. et al.Gpt4point: A Unified Framework for Point-Language Understanding and Generation 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023 IEEE 26407\u201326417.","DOI":"10.1109\/CVPR52733.2024.02495"},{"key":"e_1_2_10_27_2","doi-asserted-by":"crossref","unstructured":"HanK. WangY. TianQ. GuoJ. XuC. andXuC. Ghostnet: More Features From Cheap Operations 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019 IEEE 1577\u20131586.","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"e_1_2_10_28_2","unstructured":"WuZ. SongS. andKhoslaA. et al.3d Shapenets: A Deep Representation for Volumetric Shapes 2015 Computer Vision and Pattern Recognition."},{"key":"e_1_2_10_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980238"},{"key":"e_1_2_10_30_2","doi-asserted-by":"crossref","unstructured":"LiuY. FanB. MengG. LuJ. XiangS. andPanC. Densepoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) 2019 IEEE 5238\u20135247.","DOI":"10.1109\/ICCV.2019.00534"},{"key":"e_1_2_10_31_2","unstructured":"GuoM. H. CaiJ. X. LiuZ. N. MuT. J. andHuS. M. Pct: Point Cloud Transformer 2020."},{"key":"e_1_2_10_32_2","doi-asserted-by":"crossref","unstructured":"YuX. TangL. RaoY. HuangT. ZhouJ. andLuJ. Pointbert: Pre-Training 3d Point Cloud Transformers With Masked Point Modeling 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021 IEEE 19291\u201319300.","DOI":"10.1109\/CVPR52688.2022.01871"}],"container-title":["IET Computers &amp; Digital Techniques"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cdt2\/7934018","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/cdt2\/7934018","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cdt2\/7934018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T15:08:03Z","timestamp":1772982483000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/cdt2\/7934018"}},"subtitle":[],"editor":[{"given":"Wassim","family":"Alexan","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1049\/cdt2\/7934018"],"URL":"https:\/\/doi.org\/10.1049\/cdt2\/7934018","archive":["Portico"],"relation":{},"ISSN":["1751-8601","1751-861X"],"issn-type":[{"value":"1751-8601","type":"print"},{"value":"1751-861X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2024-11-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"7934018"}}