{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:58:57Z","timestamp":1776182337418,"version":"3.50.1"},"reference-count":54,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2020,2,14]],"date-time":"2020-02-14T00:00:00Z","timestamp":1581638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["41801390; 41801387"],"award-info":[{"award-number":["41801390; 41801387"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the National Key R&amp;D Program of China","award":["2017YFB0503004"],"award-info":[{"award-number":["2017YFB0503004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Semantic feature learning on 3D point clouds is quite challenging because of their irregular and unordered data structure. In this paper, we propose a novel structure-aware convolution (SAC) to generalize deep learning on regular grids to irregular 3D point clouds. Similar to the template-matching process of convolution on 2D images, the key of our SAC is to match the point clouds\u2019 neighborhoods with a series of 3D kernels, where each kernel can be regarded as a \u201cgeometric template\u201d formed by a set of learnable 3D points. Thus, the interested geometric structures of the input point clouds can be activated by the corresponding kernels. To verify the effectiveness of the proposed SAC, we embedded it into three recently developed point cloud deep learning networks (PointNet, PointNet++, and KCNet) as a lightweight module, and evaluated its performance on both classification and segmentation tasks. Experimental results show that, benefiting from the geometric structure learning capability of our SAC, all these back-end networks achieved better classification and segmentation performance (e.g., +2.77% mean accuracy for classification and +4.99% mean intersection over union (IoU) for segmentation) with few additional parameters. Furthermore, results also demonstrate that the proposed SAC is helpful in improving the robustness of networks with the constraints of geometric structures.<\/jats:p>","DOI":"10.3390\/rs12040634","type":"journal-article","created":{"date-parts":[[2020,2,20]],"date-time":"2020-02-20T03:20:03Z","timestamp":1582168803000},"page":"634","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Structure-Aware Convolution for 3D Point Cloud Classification and Segmentation"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6477-6172","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"first","affiliation":[{"name":"State Key Laboratory for Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4394-1989","authenticated-orcid":false,"given":"Yuxuan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8589-5637","authenticated-orcid":false,"given":"Shenman","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jixing","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Highway, Chang\u2019an University, Xi\u2019an 710064, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5011-9446","authenticated-orcid":false,"given":"Pengjie","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,2,14]]},"reference":[{"key":"ref_1","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, Honolulu, HI, USA."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Liu, Y., Fan, B., Xiang, S., and Pan, C. (2019, January 16\u201320). Relation-Shape Convolutional Neural Network for Point Cloud Analysis. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00910"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Zheng, M., Wu, H., and Li, Y. (2019). An adaptive end-to-end classification approach for mobile laser scanning point clouds based on knowledge in urban scenes. Remote Sens., 11.","DOI":"10.3390\/rs11020186"},{"key":"ref_4","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2020, February 14). ImageNet Classification with Deep Convolutional Neural Networks. Available online: http:\/\/papers.nips.cc\/paper\/4824-imagenet-classification-with-deep-convolutional-neural-networ."},{"key":"ref_5","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","volume":"40","author":"Chen","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Wang, L., Huang, Y., Hou, Y., Zhang, S., and Shan, J. (2019, January 16\u201320). Graph Attention Convolution for Point Cloud Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01054"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Graham, B., Engelcke, M., and van der Maaten, L. (2018, January 18\u201323). 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00961"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Tchapmi, L.P., Choy, C.B., Armeni, I., Gwak, J., and Savarese, S. (2017, January 10\u201312). SEGCloud: Semantic Segmentation of 3D Point Clouds. Proceedings of the 2017 International Conference on 3D Vision, Qingdao, China.","DOI":"10.1109\/3DV.2017.00067"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Yang, Z., Jiang, W., Xu, B., Zhu, Q., Jiang, S., and Huang, W. (2017). A convolutional neural network-based 3D semantic labeling method for ALS point clouds. Remote Sens., 9.","DOI":"10.3390\/rs9090936"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Gadelha, M., Wang, R., and Maji, S. (2018, January 8\u201314). Multiresolution Tree Networks for 3D Point Cloud Processing. Proceedings of the European Conference on Computer Vision, Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_7"},{"key":"ref_12","unstructured":"Maturana, D., and Scherer, S. (October, January 28). VoxNet: A 3D Convolutional Neural Network for Real-Time Object Recognition. Proceedings of the IEEE International Conference on Intelligent Robots and Systems, Hamburg, Germany."},{"key":"ref_13","unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., and Xiao, J. (2015, January 7\u201312). 3D ShapeNets: A Deep Representation for Volumetric Shapes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wang, L., Huang, Y., Shan, J., and He, L. (2018). MSNet: Multi-scale convolutional network for point cloud classification. Remote Sens., 10.","DOI":"10.3390\/rs10040612"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Feng, Y., Zhang, Z., Zhao, X., Ji, R., and Gao, Y. (2018, January 18\u201323). GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00035"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Su, H., Maji, S., Kalogerakis, E., and Learned-Miller, E. (2015, January 11\u201318). Multi-view Convolutional Neural Networks for 3D Shape Recognition. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Kalogerakis, E., Averkiou, M., Maji, S., and Chaudhuri, S. (2017, January 21\u201326). 3D Shape Segmentation with Projective Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.702"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.cag.2017.05.011","article-title":"A multi-view recurrent neural network for 3D mesh segmentation","volume":"66","author":"Le","year":"2017","journal-title":"Comput. Graph."},{"key":"ref_19","unstructured":"Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2020, February 14). PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. Available online: http:\/\/papers.nips.cc\/paper\/7095-pointnet-deep-hierarchical-feature-learning-on-point-se."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Shen, Y., Feng, C., Yang, Y., and Tian, D. (2018, January 18\u201323). Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00478"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Rusu, R.B., Blodow, N., and Beetz, M. (2009, January 12\u201317). Fast Point Feature Histograms (FPFH) for 3D registration. Proceedings of the IEEE International Conference on Robotics and Automation, Kobe, Japan.","DOI":"10.1109\/ROBOT.2009.5152473"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.cviu.2014.04.011","article-title":"SHOT: Unique signatures of histograms for surface and texture description","volume":"125","author":"Salti","year":"2014","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1109\/JSTARS.2019.2951293","article-title":"Classification of LiDAR Point Clouds Using Supervoxel-Based Detrended Feature and Perception-Weighted Graphical Model","volume":"13","author":"Xu","year":"2019","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.isprsjprs.2013.11.001","article-title":"Contextual classification of lidar data and building object detection in urban areas","volume":"87","author":"Niemeyer","year":"2014","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"271","DOI":"10.5194\/isprsannals-II-3-W4-271-2015","article-title":"Contextual classification of point cloud data by exploiting individual 3D neigbourhoods","volume":"2","author":"Weinmann","year":"2015","journal-title":"ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"8408","DOI":"10.1080\/01431161.2013.838710","article-title":"Object class segmentation of massive 3D point clouds of urban areas using point cloud topology","volume":"34","author":"Richter","year":"2013","journal-title":"Int. J. Remote Sens."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1177\/0278364912461538","article-title":"Contextually guided semantic labeling and search for three-dimensional point clouds","volume":"32","author":"Anand","year":"2013","journal-title":"Int. J. Robot. Res."},{"key":"ref_28","unstructured":"Chen, G., and Maggioni, M. (2011, January 2\u20136). Multiscale Geometric Dictionaries for Point-Cloud Data. Proceedings of the International Conference on Sampling Theory and Applications (SampTA), Singapore."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"3309","DOI":"10.1109\/TGRS.2016.2514508","article-title":"A Multilevel Point-Cluster-Based Discriminative Feature for ALS Point Cloud Classification","volume":"54","author":"Zhang","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"177","DOI":"10.5194\/isprs-annals-III-3-177-2016","article-title":"Fast semantic segmentation of 3D point clouds with strongly varying density","volume":"3","author":"Hackel","year":"2016","journal-title":"ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"3749","DOI":"10.3390\/rs5083749","article-title":"SVM-Based classification of segmented airborne LiDAR point clouds in urban areas","volume":"5","author":"Zhang","year":"2013","journal-title":"Remote Sens."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1109\/LGRS.2017.2669304","article-title":"LiDAR Data Classification Using Extinction Profiles and a Composite Kernel Support Vector Machine","volume":"14","author":"Ghamisi","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Lodha, S.K., Fitzpatrick, D.M., and Helmbold, D.P. (2007, January 21\u201323). Aerial Lidar Data Classification Using AdaBoost. Proceedings of the 6th International Conference on 3-D Digital Imaging and Modeling, Montreal, QC, Canada.","DOI":"10.1109\/3DIM.2007.10"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Niemeyer, J., Rottensteiner, F., and Soergel, U. (2013, January 21\u201323). Classification of Urban LiDAR Data Using Conditional Random Field and Random Forests. Proceedings of the Joint Urban Remote Sensing Event, Sao Paulo, Brazil.","DOI":"10.1109\/JURSE.2013.6550685"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Ni, H., Lin, X., and Zhang, J. (2017). Classification of ALS point cloud with improved point cloud segmentation and random forests. Remote Sens., 9.","DOI":"10.3390\/rs9030288"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Najafi, M., Namin, S.T., Salzmann, M., and Petersson, L. (2014, January 6\u201312). Non-Associative Higher-Order Markov Networks for Point Cloud Classification. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10602-1_33"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"263","DOI":"10.5194\/isprsannals-I-3-263-2012","article-title":"Conditional random fields for LiDAR point cloud classification in complex urban areas","volume":"3","author":"Niemeyer","year":"2012","journal-title":"ISPRS Ann. Photogramm. Remote Sens. Spatioal Inf. Sci."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"655","DOI":"10.5194\/isprs-archives-XLI-B3-655-2016","article-title":"Hierarchical higher order crf for the classification of airborne lidar point clouds in urban areas","volume":"41","author":"Niemeyer","year":"2016","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.isprsjprs.2014.04.022","article-title":"A global optimization approach to roof segmentation from airborne lidar point clouds","volume":"94","author":"Yan","year":"2014","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Le, T., and Duan, Y. (2018, January 18\u201323). PointGrid: A Deep Network for 3D Shape Understanding. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00959"},{"key":"ref_41","first-page":"1","article-title":"O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis","volume":"36","author":"Wang","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/MSP.2017.2693418","article-title":"Geometric Deep Learning: Going beyond Euclidean data","volume":"34","author":"Bronstein","year":"2017","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Simonovsky, M., and Komodakis, N. (2017, January 21\u201326). Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.11"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Yi, L., Su, H., Guo, X., and Guibas, L.J. (2017, January 21\u201326). SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.697"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Landrieu, L., and Simonovsky, M. (2018, January 18\u201323). Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00479"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Engelmann, F., Kontogianni, T., Hermans, A., and Leibe, B. (2017, January 22\u201329). Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds. Proceedings of the IEEE International Conference on Computer Vision Workshop, Venice, Italy.","DOI":"10.1109\/ICCVW.2017.90"},{"key":"ref_47","unstructured":"Ravanbakhsh, S., Schneider, J., and Poczos, B. (2016). Deep Learning with Sets and Point Clouds. arXiv Prepr."},{"key":"ref_48","unstructured":"Zaheer, M., Kottur, S., Ravanbakhsh, S., Poczos, B., Salakhutdinov, R., and Smola, A. (2020, February 14). Deep Sets. Available online: http:\/\/papers.nips.cc\/paper\/6931-deep-sets."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Xu, Y., Fan, T., Xu, M., Zeng, L., and Qiao, Y. (2018, January 8\u201314). Spidercnn: Deep Learning on Point Sets with Parameterized Convolutional Filters. Proceedings of the European Conference on Computer Vision, Munich, Germany.","DOI":"10.1007\/978-3-030-01237-3_6"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Komarichev, A., Zhong, Z., and Hua, J. (2019, January 16\u201320). A-CNN: Annularly Convolutional Neural Networks on Point Clouds. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00760"},{"key":"ref_51","unstructured":"Thomas, H., Qi, C.R., Deschaud, J.-E., Marcotegui, B., Goulette, F., and Guibas, L.J. (November, January 27). KPConv: Flexible and Deformable Convolution for Point Clouds. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3197517.3201301","article-title":"Point convolutional neural networks by extension operators","volume":"37","author":"Atzmon","year":"2018","journal-title":"ACM Trans. Graph."},{"key":"ref_53","unstructured":"Armeni, I., Sener, O., Zamir, A.R., Jiang, H., Brilakis, I., Fischer, M., and Savarese, S. (July, January 26). 3D Semantic Parsing of Large-Scale Indoor Spaces. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_54","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/4\/634\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T08:57:53Z","timestamp":1760173073000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/4\/634"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,14]]},"references-count":54,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2020,2]]}},"alternative-id":["rs12040634"],"URL":"https:\/\/doi.org\/10.3390\/rs12040634","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,14]]}}}