{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:16:51Z","timestamp":1790266611535,"version":"4.1.0"},"reference-count":49,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T00:00:00Z","timestamp":1778544000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"R&D Program of Beijing Municipal Education Commission","award":["KM202410011002"],"award-info":[{"award-number":["KM202410011002"]}]},{"award":["KM202410011002"],"award-info":[{"award-number":["KM202410011002"]}],"id":[{"id":"https:\/\/ror.org\/04bpn6s66","id-type":"ROR","asserted-by":"publisher"}]},{"name":"BTBU Research Foundation for Youth Scholars","award":["BRFYS2025"],"award-info":[{"award-number":["BRFYS2025"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Point cloud semantic segmentation is a vital task in 3D computer vision. However, the inherent sparsity of point clouds complicates the segmentation process. In contexts such as autonomous driving, moving objects frequently exhibit motion blur, which adversely affects semantic segmentation performance. These challenges hinder the practical application of point cloud semantic segmentation. To address these issues, this paper presents a novel semantic segmentation method that integrates sparse point cloud completion with multi-feature fusion. Specifically, the study emphasizes the development of efficient strategies for constructing and training point cloud completion models, aiming to expedite model parameter training while maximizing completion accuracy. Additionally, a semantic segmentation model is introduced that combines motion feature-enhanced instance features with semantic features, thereby enhancing adaptability to moving objects. Moreover, point cloud completion and semantic segmentation are linked in an end-to-end pipeline, facilitating accurate semantic segmentation of sparse point clouds in dynamic environments. During the experimental phase, publicly available Lidar point cloud datasets, including SemanticKITTI and the millimeter-wave radar dataset RADIal, are utilized to evaluate the proposed method against classical approaches in terms of point cloud completion performance and semantic segmentation effectiveness, thereby demonstrating the reliability of the proposed method.<\/jats:p>","DOI":"10.3390\/s26103056","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:04:36Z","timestamp":1778601876000},"page":"3056","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Semantic Segmentation Method for Sparse Point Clouds Based on Straight Flow Completion and Multi-Feature Fusion"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2251-6844","authenticated-orcid":false,"given":"Tong","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyuan","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4234-1260","authenticated-orcid":false,"given":"Chongchong","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yewang","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Yang, Y., Yu, S., and Xiao, J. (2026). Robust LiDAR-based train detection via point cloud segmentation for railway safety. Sensors, 26.","DOI":"10.3390\/s26051514"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Ahmadi, A., Mostafavi, M.A., Morales, E., and Sabo, N. (2026). Characterizing pedestrian network from segmentation 3D point clouds for accessibility assessment: A virtual robotic approach. Sensors, 26.","DOI":"10.3390\/s26072172"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Tian, D., Shi, J., Li, J., and Gong, M. (2025). Point cloud completion network based on multi-dimensional adaptive feature fusion and informative channel attention mechanism. Sensors, 25.","DOI":"10.2139\/ssrn.5208544"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Su, H., Maji, S., Kalogerakis, E., and Learned-Miller, E. (2015, January 7\u201313). Multi-view convolutional neural networks for 3d shape recognition. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Wu, B., Wan, A., Yue, X., and Keutzer, K. (2018, January 21\u201325). Squeezeseg: Convolutional neural nets with recurrent CRF for real-time road-object segmentation from 3d lidar point cloud. Proceedings of the 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia.","DOI":"10.1109\/ICRA.2018.8462926"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wu, B., Zhou, X., Zhao, S., Yue, X., and Keutzer, K. (2019, January 12). Squeezesegv2: Improved model structure and unsupervised domain adaptation for road-object segmentation from a lidar point cloud. Proceedings of the 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada.","DOI":"10.1109\/ICRA.2019.8793495"},{"key":"ref_7","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 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00961"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhu, X., Zhou, H., Wang, T., Hong, F., Ma, Y., and Li, W. (2021, January 20\u201325). Cylindrical and asymmetrical 3D convolution networks for lidar segmentation. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00981"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Riegler, G., Osman Ulusoy, A., and Geiger, A. (2017, January 21\u201326). Octnet: Learning deep 3d representations at high resolutions. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.701"},{"key":"ref_10","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 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA."},{"key":"ref_11","unstructured":"Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017, January 4\u20139). Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Proceedings of the 31st Annual Conference on Neural Information Processing Systems (NIPS), Long Beach, CA, USA."},{"key":"ref_12","unstructured":"Bengio, S., Wallach, H., Larochelle, H., Grauman, K., and CesaBianchi, N. (2018, January 2\u20138). Pointcnn: Convolution on X-transformed points. Proceedings of the 32nd Conference on Neural Information Processing Systems (NIPS), Montreal, QC, Canada."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., and Guibas, L. (November, January 27). KPConv: Flexible and deformable convolution for point clouds. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Xu, Q., Sun, X., Wu, C.Y., Wang, P., and Neumann, U. (2020, January 5). Grid-GCN for fast and scalable point cloud learning. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00570"},{"key":"ref_15","first-page":"25362","article-title":"CrossModalSync: Joint temporal-spatial fusion for semantic scene segmentation in large-scale scenes","volume":"15","author":"Tan","year":"2025","journal-title":"Sci. Res."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"5704720","DOI":"10.1109\/TGRS.2023.3322579","article-title":"MCTNet: Multiscale cross-attention-based Transformer network for semantic segmentation of large-scale point cloud","volume":"61","author":"Guo","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"22862","DOI":"10.1109\/TITS.2022.3195555","article-title":"Comprehensive review of deep learning-based 3D point cloud completion processing and analysis","volume":"23","author":"Fei","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Huang, Z., Yu, Y., Xu, J., Ni, F., and Le, X. (2020, January 13\u201319). PF-Net: Point fractal network for 3d point cloud completion. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00768"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhang, W., Yan, Q., and Xiao, C. (2020). Detail preserved point cloud completion via separated feature aggregation. Proceedings of the European Conference on Computer Vision (ECCV), Springer Nature Link.","DOI":"10.1007\/978-3-030-58595-2_31"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Hua, B.S., Tran, M.K., and Yeung, S.K. (2018, January 18\u201323). Pointwise convolutional neural networks. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00109"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, X., Ang, M.H., and Lee, G.H. (2021, January 10\u201317). Voxel-based network for shape completion by leveraging edge generation. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.01294"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1145\/3326362","article-title":"Dynamic graph CNN for learning on point clouds","volume":"38","author":"Wang","year":"2019","journal-title":"ACM Trans. Graph."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"7081","DOI":"10.1109\/LRA.2021.3097081","article-title":"Graph-guided deformation for point cloud completion","volume":"6","author":"Shi","year":"2021","journal-title":"IEEE Rob. Autom Lett."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Yang, Y., Feng, C., Shen, Y., and Tian, D. (2018, January 18\u201323). Foldingnet: Point cloud auto-encoder via deep grid deformation. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00029"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Xie, C., Wang, C., Zhang, B., Yang, H., Chen, D., and Wen, F. (2021, January 20\u201325). Style-based point generator with adversarial rendering for point cloud completion. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00459"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P., and Koltun, V. (2021, January 10\u201317). Point transformer. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"538","DOI":"10.11834\/jig.210510","article-title":"Multi-scale transformer based point cloud completion network","volume":"27","author":"Liu","year":"2022","journal-title":"J. Image Graph."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Spurek, P., Kasymov, A., Mazur, M., Janik, D., Tadeja, S.K., and Struski, L. (2022, January 23\u201327). Hyperpocket: Generative point cloud completion. Proceedings of the 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Kyoto, Japan.","DOI":"10.1109\/IROS47612.2022.9981829"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Wang, X., Ang, M.H., and Lee, G.H. (2020\u201324, January 24). Point cloud completion by learning shape priors. Proceedings of the 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA.","DOI":"10.1109\/IROS45743.2020.9340862"},{"key":"ref_30","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Luo, S., and Hu, W. (2021, January 20\u201325). Diffusion probabilistic models for 3D point cloud generation. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhou, L., Du, Y., and Wu, J. (2021, January 20\u201325). 3D shape generation and completion through point-voxel diffusion. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/ICCV48922.2021.00577"},{"key":"ref_33","unstructured":"Kim, H., Lee, H., Kang, W.H., Lee, J.Y., and Kim, N.S. (2021). Softflow: Probabilistic framework for normalizing flow on manifolds. Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS), Springer International Publishing."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Yang, G., Huang, X., Hao, Z., Liu, M., Belongie, S., and Hariharan, B. (November, January 27). Pointflow: 3D point cloud generation with continuous normalizing flows. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00464"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, J., Zhang, X., and Song, H. (2026). Robust object detection in adverse weather conditions: ECL-YOLOv11 for automotive vision systems. Sensors, 26.","DOI":"10.3390\/s26010304"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J.Y., and Savarese, S. (2019, January 15\u201320). 4D spatio-temporal convnets: Minkowski convolutional neural networks. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2181","DOI":"10.1109\/TPAMI.2022.3161735","article-title":"Point 4D transformer networks for spatio-temporal modeling in point cloud videos","volume":"45","author":"Fan","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Shi, H., Lin, G., Wang, H., Huang, T., and Wang, Z. (2020, January 13\u201319). Spsequencenet: Semantic segmentation network on 4d point clouds. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00463"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Duerr, F., Pfaller, M., Weigel, H., and Beyerer, J. (2021, January 19). Lidar-based recurrent 3D semantic segmentation with temporal memory alignment. Proceedings of the 2020 International Conference on 3D Vision (3DV), Fukuoka, Japan.","DOI":"10.1109\/3DV50981.2020.00088"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Chen, X., Xu, S., Zou, X., Cao, T., Yeung, D., and Fang, L. (2023, January 1\u20136). Svqnet: Sparse voxel-adjacent query network for 4d spatio-temporal lidar semantic segmentation. Proceedings of the 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.00787"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Yan, X., Gao, J., Zheng, C., Zheng, C., Zhang, R.M., Cui, S.G., and Li, Z. (2022). 2DPASS: 2D priors assisted semantic segmentation on lidar point clouds. Proceedings of the 17th European Conference on Computer Vision (ECCV), Springer Nature.","DOI":"10.1007\/978-3-031-19815-1_39"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Wu, X., Hou, Y., Huang, X., Lin, B., He, T., and Zhu, X. (2024, January 16\u201322). TASeg: Temporal aggregation network for LiDAR semantic segmentation. Proceedings of the 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01450"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"15339","DOI":"10.1109\/TASE.2025.3568001","article-title":"SegNet4D: Efficient instance-aware 4D semantic segmentation for LiDAR point cloud","volume":"22","author":"Wang","year":"2025","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Schutt, P., Rosu, R.A., and Behnke, S. (2022, January 23\u201327). Abstract flow for temporal semantic segmentation on the permutohedral lattice. Proceedings of the 2022 International Conference on Robotics and Automation (ICRA), Philadelphia, PA, USA.","DOI":"10.1109\/ICRA46639.2022.9811818"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Liu, J., Chang, C., Liu, J., Wu, X., Ma, L., and Qi, X. (2023, January 17\u201324). MarS3D: A plug-and-play motion-aware model for semantic segmentation on multi-scan 3d point clouds. Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00904"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"9739","DOI":"10.1109\/LRA.2022.3191040","article-title":"Meta-RangeSeg: Lidar sequence semantic segmentation using multiple feature aggregation","volume":"7","author":"Wang","year":"2022","journal-title":"IEEE Rob. Autom. Lett."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Feng, T., Wang, W., Wang, X., Yang, Y., and Zheng, Q. (2023, January 1\u20136). Clustering based point cloud representation learning for 3D analysis. Proceedings of the 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.00761"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Li, E., Casas, S., and Urtasun, R. (2023, January 1\u20136). Memoryseg: Online lidar semantic segmentation with a latent memory. Proceedings of the 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.00075"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Puy, G., Boulch, A., and Marlet, R. (2023, January 1\u20136). Using a waffle iron for automotive point cloud semantic segmentation. Proceedings of the 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.00313"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/10\/3056\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:15:31Z","timestamp":1778602531000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/10\/3056"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,12]]},"references-count":49,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["s26103056"],"URL":"https:\/\/doi.org\/10.3390\/s26103056","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,12]]}}}