{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T13:20:59Z","timestamp":1771852859277,"version":"3.50.1"},"reference-count":32,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2023,10,24]],"date-time":"2023-10-24T00:00:00Z","timestamp":1698105600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2022M723377"],"award-info":[{"award-number":["2022M723377"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Point cloud-based retrieval for place recognition is essential in robotic applications like autonomous driving or simultaneous localization and mapping. However, this remains challenging in complex real-world scenes. Existing methods are sensitive to noisy, low-density point clouds and require extensive storage and computation, posing limitations for hardware-limited scenarios. To overcome these challenges, we propose LWR-Net, a lightweight place recognition network for efficient and robust point cloud retrieval in noisy, low-density conditions. Our approach incorporates a fast dilated sampling and grouping module with a residual MLP structure to learn geometric features from local neighborhoods. We also introduce a lightweight attentional weighting module to enhance global feature representation. By utilizing the Generalized Mean pooling structure, we aggregated the global descriptor for point cloud retrieval. We validated LWR-Net\u2019s efficiency and robustness on the Oxford robotcar dataset and three in-house datasets. The results demonstrate that our method efficiently and accurately retrieves matching scenes while being more robust to variations in point density and noise intensity. LWR-Net achieves state-of-the-art accuracy and robustness with a lightweight model size of 0.4M parameters. These efficiency, robustness, and lightweight advantages make our network highly suitable for robotic applications relying on point cloud-based place recognition.<\/jats:p>","DOI":"10.3390\/s23218664","type":"journal-article","created":{"date-parts":[[2023,10,24]],"date-time":"2023-10-24T11:39:04Z","timestamp":1698147544000},"page":"8664","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["LWR-Net: Robust and Lightweight Place Recognition Network for Noisy and Low-Density Point Clouds"],"prefix":"10.3390","volume":"23","author":[{"given":"Zhenghua","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Environment Science and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, China"}]},{"given":"Guoliang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Environment Science and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, China"}]},{"given":"Mingcong","family":"Shu","sequence":"additional","affiliation":[{"name":"School of Environment Science and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, China"}]},{"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,10,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1016\/j.isprsjprs.2020.12.013","article-title":"Deep regression for LiDAR-based localization in dense urban areas","volume":"172","author":"Yu","year":"2021","journal-title":"Isprs. J. Photogramm. Remote Sens."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.isprsjprs.2022.05.005","article-title":"A LiDAR-based single-shot global localization solution using a cross-section shape context descriptor","volume":"189","author":"Xu","year":"2022","journal-title":"Isprs. J. Photogramm. Remote Sens."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.isprsjprs.2016.09.004","article-title":"Localization of a mobile laser scanner via dimensional reduction","volume":"121","author":"Lehtola","year":"2016","journal-title":"Isprs. J. Photogramm. Remote Sens."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Abdelaziz, N., and El-Rabbany, A. (2023). INS\/LIDAR\/Stereo SLAM Integration for Precision Navigation in GNSS-Denied Environments. Sensors, 23.","DOI":"10.3390\/s23177424"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Wozniak, P., and Ozog, D. (2023). Cross-Domain Indoor Visual Place Recognition for Mobile Robot via Generalization Using Style Augmentation. Sensors, 23.","DOI":"10.3390\/s23136134"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/j.isprsjprs.2021.12.011","article-title":"An improved lightweight deep neural network with knowledge distillation for local feature extraction and visual localization using images and LiDAR point clouds","volume":"184","author":"Shi","year":"2022","journal-title":"Isprs. J. Photogramm. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Kadhim, I., and Abed, F.M. (2023). A Critical Review of Remote Sensing Approaches and Deep Learning Techniques in Archaeology. Sensors, 23.","DOI":"10.3390\/s23062918"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Tarsha Kurdi, F., Amakhchan, W., Gharineiat, Z., Boulaassal, H., and El Kharki, O. (2023). Contribution of Geometric Feature Analysis for Deep Learning Classification Algorithms of Urban LiDAR Data. Sensors, 23.","DOI":"10.3390\/s23177360"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"4242","DOI":"10.1109\/JSEN.2018.2815956","article-title":"Robust Place Recognition and Loop Closing in Laser-Based SLAM for UGVs in Urban Environments","volume":"18","author":"Cao","year":"2018","journal-title":"IEEE Sens. J."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Cop, K.P., Borges, P.V.K., and Dub\u00e9, R. (2018, January 21\u201325). Delight: An Efficient Descriptor for Global Localisation Using LiDAR Intensities. Proceedings of the 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, QLD, Australia.","DOI":"10.1109\/ICRA.2018.8460940"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"R\u00f6hling, T., Mack, J., and Schulz, D. (October, January 28). A fast histogram-based similarity measure for detecting loop closures in 3-D LIDAR data. Proceedings of the 2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany.","DOI":"10.1109\/IROS.2015.7353454"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Uy, M.A., and Lee, G.H. (2018, January 18\u201323). PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00470"},{"key":"ref_13","unstructured":"Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2017, January 21\u201326). PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., and Sivic, J. (2016, January 27\u201330). NetVLAD: CNN Architecture for Weakly Supervised Place Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, W., and Xiao, C. (2019, January 15\u201320). PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01272"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhou, S., Suo, C., Yin, P., Chen, W., Wang, H., Li, H., and Liu, Y. (November, January 27). LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, South Korea.","DOI":"10.1109\/ICCV.2019.00292"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Sun, Q., Liu, H., He, J., Fan, J.Z., and Du, X. (2020, January 26\u201329). DAGC: Employing Dual Attention and Graph Convolution for Point Cloud based Place Recognition. Proceedings of the 2020 International Conference on Multimedia Retrieval, Dublin, Ireland.","DOI":"10.1145\/3372278.3390693"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1258","DOI":"10.1109\/TIP.2021.3136714","article-title":"Efficient 3D Point Cloud Feature Learning for Large-Scale Place Recognition","volume":"31","author":"Hui","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Komorowski, J. (2021, January 5\u20139). MinkLoc3D: Point Cloud Based Large-Scale Place Recognition. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Virtual.","DOI":"10.1109\/WACV48630.2021.00183"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., and Savarese, S. (2019, January 16\u201320). 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Komorowski, J., Wysocza\u0144ska, M., and Trzcinski, T. (2021, January 18\u201322). MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition. Proceedings of the 2021 International Joint Conference on Neural Networks (IJCNN), Virtual.","DOI":"10.1109\/IJCNN52387.2021.9533373"},{"key":"ref_22","unstructured":"Xu, T., Guo, Y., Lai, Y.-K., and Zhang, S.-H. (2021). TransLoc3D: Point Cloud based Large-scale Place Recognition using Adaptive Receptive Fields. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1655","DOI":"10.1109\/TPAMI.2018.2846566","article-title":"Fine-Tuning CNN Image Retrieval with No Human Annotation","volume":"41","author":"Tolias","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1177\/0278364916679498","article-title":"1 year, 1000 km: The Oxford RobotCar dataset","volume":"36","author":"Maddern","year":"2017","journal-title":"Int. J. Robot. Res."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1145\/355744.355745","article-title":"An algorithm for finding best matches in logarithmic expected time","volume":"3","author":"Freidman","year":"1977","journal-title":"ACM Trans. Math. Softw. (TOMS)"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ram, P., and Sinha, K. (2019, January 4\u20138). Revisiting kd-tree for Nearest Neighbor Search. Proceedings of the KDD \u201819: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.","DOI":"10.1145\/3292500.3330875"},{"key":"ref_27","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017). Attention is All you Need. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Xia, Y., Xu, Y., Li, S., Wang, R., Du, J., Cremers, D., and Stilla, U. (2021, January 20\u201325). SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01119"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Zhao, C., Adolfsson, D., Su, S., Gao, Y., Duckett, T., and Sun, L. (June, January 30). NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representation. Proceedings of the 2021 IEEE International Conference on Robotics and Automation (ICRA), Xi\u2019an, China.","DOI":"10.1109\/ICRA48506.2021.9560932"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Hui, L., Yang, H., Cheng, M., Xie, J., and Yang, J. (2021, January 10\u201317). Pyramid Point Cloud Transformer for Large-Scale Place Recognition. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Virtual.","DOI":"10.1109\/ICCV48922.2021.00604"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Komorowski, J. (2022, January 21\u201325). Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Training. Proceedings of the 2022 26th International Conference on Pattern Recognition (ICPR), Montr\u00e9al, QC, Canada.","DOI":"10.1109\/ICPR56361.2022.9956458"},{"key":"ref_32","first-page":"551","article-title":"SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition","volume":"36","author":"Fan","year":"2022","journal-title":"Proc. AAAI Conf. Artif. Intell."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/21\/8664\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:10:49Z","timestamp":1760130649000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/21\/8664"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,24]]},"references-count":32,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2023,11]]}},"alternative-id":["s23218664"],"URL":"https:\/\/doi.org\/10.3390\/s23218664","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,24]]}}}