{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T04:18:00Z","timestamp":1783225080270,"version":"3.54.6"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","award":["348008"],"award-info":[{"award-number":["348008"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","award":["348479"],"award-info":[{"award-number":["348479"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.cviu.2026.104859","type":"journal-article","created":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T15:15:28Z","timestamp":1782573328000},"page":"104859","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Trainable pointwise decoder module and virtual range image-guided copy-rotate-paste augmentation for point cloud segmentation"],"prefix":"10.1016","volume":"270","author":[{"given":"Bike","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antti","family":"Tikanm\u00e4ki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juha","family":"R\u00f6ning","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104859_b1","doi-asserted-by":"crossref","unstructured":"Ando, A., Gidaris, S., Bursuc, A., Puy, G., Boulch, A., Marlet, R., 2023. RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving. In: Computer Vision and Pattern Recognition. pp. 5240\u20135250.","DOI":"10.1109\/CVPR52729.2023.00507"},{"key":"10.1016\/j.cviu.2026.104859_b2","doi-asserted-by":"crossref","unstructured":"Behley, J., Garbade, M., Milioto, A., Quenzel, J., Behnke, S., Stachniss, C., Gall, J., 2019. Semantickitti: A dataset for semantic scene understanding of lidar sequences. In: International Conference on Computer Vision. pp. 9297\u20139307.","DOI":"10.1109\/ICCV.2019.00939"},{"key":"10.1016\/j.cviu.2026.104859_b3","doi-asserted-by":"crossref","unstructured":"Charles, R.Q., Su, H., Kaichun, M., Guibas, L.J., 2017. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. In: 20Computer Vision and Pattern Recognition. pp. 77\u201385.","DOI":"10.1109\/CVPR.2017.16"},{"key":"10.1016\/j.cviu.2026.104859_b4","first-page":"1","article-title":"Filling missing values matters for range image-based point cloud segmentation","author":"Chen","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.cviu.2026.104859_b5","doi-asserted-by":"crossref","first-page":"2209","DOI":"10.1109\/LSP.2025.3571409","article-title":"Copy-rotate-paste augmentation for point cloud segmentation","volume":"32","author":"Chen","year":"2025","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.cviu.2026.104859_b6","doi-asserted-by":"crossref","unstructured":"Chen, X., Milioto, A., Palazzolo, E., Gigu\u00e8re, P., Behley, J., Stachniss, C., 2019. SuMa++: Efficient LiDAR-based Semantic SLAM. In: International Conference on Intelligent Robots and Systems. pp. 4530\u20134537.","DOI":"10.1109\/IROS40897.2019.8967704"},{"key":"10.1016\/j.cviu.2026.104859_b7","series-title":"An experimental study of SOTA LiDAR segmentation models","author":"Chen","year":"2025"},{"key":"10.1016\/j.cviu.2026.104859_b8","doi-asserted-by":"crossref","unstructured":"Cheng, H., Han, X., Xiao, G., 2022. Cenet: Toward concise and efficient lidar semantic segmentation for autonomous driving. In: International Conference on Multimedia and Expo. pp. 01\u201306.","DOI":"10.1109\/ICME52920.2022.9859693"},{"key":"10.1016\/j.cviu.2026.104859_b9","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., Savarese, S., 2019. 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. In: Computer Vision and Pattern Recognition. pp. 3070\u20133079.","DOI":"10.1109\/CVPR.2019.00319"},{"key":"10.1016\/j.cviu.2026.104859_b10","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N., 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In: International Conference on Learning Representations."},{"issue":"2","key":"10.1016\/j.cviu.2026.104859_b11","doi-asserted-by":"crossref","first-page":"3795","DOI":"10.1109\/LRA.2022.3148457","article-title":"Panoptic nuscenes: A large-scale benchmark for lidar panoptic segmentation and tracking","volume":"7","author":"Fong","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.cviu.2026.104859_b12","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1016\/j.cviu.2017.06.006","article-title":"A study of the effect of noise and occlusion on the accuracy of convolutional neural networks applied to 3D object recognition","volume":"164","author":"Garcia-Garcia","year":"2017","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104859_b13","series-title":"Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.cviu.2026.104859_b14","doi-asserted-by":"crossref","unstructured":"Hu, Q., Yang, B., Xie, L., Rosa, S., Guo, Y., Wang, Z., Trigoni, N., Markham, A., 2020. Randla-net: Efficient semantic segmentation of large-scale point clouds. In: Computer Vision and Pattern Recognition. pp. 11108\u201311117.","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"10.1016\/j.cviu.2026.104859_b15","series-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","author":"Iandola","year":"2016"},{"key":"10.1016\/j.cviu.2026.104859_b16","series-title":"Kprnet: Improving projection-based LiDAR semantic segmentation","author":"Kochanov","year":"2020"},{"key":"10.1016\/j.cviu.2026.104859_b17","doi-asserted-by":"crossref","unstructured":"Kong, L., Liu, Y., Chen, R., Ma, Y., Zhu, X., Li, Y., Hou, Y., Qiao, Y., Liu, Z., 2023a. Rethinking Range View Representation for LiDAR Segmentation. In: International Conference on Computer Vision. pp. 228\u2013240.","DOI":"10.1109\/ICCV51070.2023.00028"},{"key":"10.1016\/j.cviu.2026.104859_b18","doi-asserted-by":"crossref","unstructured":"Kong, L., Ren, J., Pan, L., Liu, Z., 2023b. LaserMix for Semi-Supervised LiDAR Semantic Segmentation. In: Conference on Computer Vision and Pattern Recognition. pp. 21705\u201321715.","DOI":"10.1109\/CVPR52729.2023.02079"},{"key":"10.1016\/j.cviu.2026.104859_b19","doi-asserted-by":"crossref","unstructured":"Lai, X., Chen, Y., Lu, F., Liu, J., Jia, J., 2023. Spherical Transformer for LiDAR-Based 3D Recognition. In: Computer Vision and Pattern Recognition. pp. 17545\u201317555.","DOI":"10.1109\/CVPR52729.2023.01683"},{"issue":"2","key":"10.1016\/j.cviu.2026.104859_b20","doi-asserted-by":"crossref","first-page":"738","DOI":"10.1109\/LRA.2021.3132059","article-title":"Multi-scale interaction for real-time lidar data segmentation on an embedded platform","volume":"7","author":"Li","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.cviu.2026.104859_b21","doi-asserted-by":"crossref","unstructured":"Li, L., Kong, X., Zhao, X., Li, W., Wen, F., Zhang, H., Liu, Y., 2021. SA-LOAM: Semantic-aided LiDAR SLAM with Loop Closure. In: International Conference on Robotics and Automation. pp. 7627\u20137634.","DOI":"10.1109\/ICRA48506.2021.9560884"},{"key":"10.1016\/j.cviu.2026.104859_b22","doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, R., Li, X., Kong, L., Yang, Y., Xia, Z., Bai, Y., Zhu, X., Ma, Y., Li, Y., Qiao, Y., Hou, Y., 2023. UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase. In: International Conference on Computer Vision. pp. 21662\u201321673.","DOI":"10.1109\/ICCV51070.2023.01980"},{"key":"10.1016\/j.cviu.2026.104859_b23","doi-asserted-by":"crossref","unstructured":"Liu, Z., Hu, H., Cao, Y., Zhang, Z., Tong, X., 2020. A Closer Look at Local Aggregation Operators in Point Cloud Analysis. In: European Conference on Computer Vision. pp. 326\u2013342.","DOI":"10.1007\/978-3-030-58592-1_20"},{"key":"10.1016\/j.cviu.2026.104859_b24","series-title":"Computer Vision and Pattern Recognition","first-page":"11966","article-title":"A ConvNet for the 2020s","author":"Liu","year":"2022"},{"key":"10.1016\/j.cviu.2026.104859_b25","doi-asserted-by":"crossref","unstructured":"Milioto, A., Vizzo, I., Behley, J., Stachniss, C., 2019. RangeNet ++: Fast and Accurate LiDAR Semantic Segmentation. In: International Conference on Intelligent Robots and Systems. pp. 4213\u20134220.","DOI":"10.1109\/IROS40897.2019.8967762"},{"key":"10.1016\/j.cviu.2026.104859_b26","doi-asserted-by":"crossref","unstructured":"Pan, Y., Gao, B., Mei, J., Geng, S., Li, C., Zhao, H., 2020. Semanticposs: A point cloud dataset with large quantity of dynamic instances. In: IEEE Intelligent Vehicles Symposium. pp. 687\u2013693.","DOI":"10.1109\/IV47402.2020.9304596"},{"key":"10.1016\/j.cviu.2026.104859_b27","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume":"vol. 30","author":"Qi","year":"2017"},{"key":"10.1016\/j.cviu.2026.104859_b28","series-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"10.1016\/j.cviu.2026.104859_b29","doi-asserted-by":"crossref","unstructured":"Tang, H., Liu, Z., Zhao, S., Lin, Y., Lin, J., Wang, H., Han, S., 2020. Searching efficient 3d architectures with sparse point-voxel convolution. In: European Conference on Computer Vision. pp. 685\u2013702.","DOI":"10.1007\/978-3-030-58604-1_41"},{"key":"10.1016\/j.cviu.2026.104859_b30","doi-asserted-by":"crossref","unstructured":"Thomas, H., Qi, C.R., Deschaud, J.-E., Marcotegui, B., Goulette, F., Guibas, L.J., 2019. Kpconv: Flexible and deformable convolution for point clouds. In: International Conference on Computer Vision. pp. 6411\u20136420.","DOI":"10.1109\/ICCV.2019.00651"},{"key":"10.1016\/j.cviu.2026.104859_b31","doi-asserted-by":"crossref","unstructured":"Triess, L.T., Peter, D., Rist, C.B., Z\u00f6llner, J.M., 2020. Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental Study. In: IEEE Intelligent Vehicles Symposium. pp. 1116\u20131121.","DOI":"10.1109\/IV47402.2020.9304631"},{"key":"10.1016\/j.cviu.2026.104859_b32","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I., 2017. Attention is all you need. In: Neural Information Processing Systems. pp. 6000\u20136010."},{"key":"10.1016\/j.cviu.2026.104859_b33","series-title":"HDL-64e S2 and S2.1 user\u2019s manual","author":"Velodyne","year":"2011"},{"key":"10.1016\/j.cviu.2026.104859_b34","first-page":"1","article-title":"NUC-net: Non-uniform cylindrical partition network for efficient lidar semantic segmentation","author":"Wang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.cviu.2026.104859_b35","first-page":"1","article-title":"TBGA-net: Trigonometric bilinear attention and global-aware aggregation network for large-scale 3D point cloud segmentation","author":"Wang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"5","key":"10.1016\/j.cviu.2026.104859_b36","doi-asserted-by":"crossref","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.","ISSN":"https:\/\/id.crossref.org\/issn\/0730-0301","issn-type":"print"},{"key":"10.1016\/j.cviu.2026.104859_b37","doi-asserted-by":"crossref","unstructured":"Wang, S., Suo, S., Ma, W.-C., Pokrovsky, A., Urtasun, R., 2018. Deep Parametric Continuous Convolutional Neural Networks. In: Computer Vision and Pattern Recognition. pp. 2589\u20132597.","DOI":"10.1109\/CVPR.2018.00274"},{"key":"10.1016\/j.cviu.2026.104859_b38","first-page":"1","article-title":"MNAT-net: Multi-scale neighborhood aggregation transformer network for point cloud classification and segmentation","author":"Wang","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.cviu.2026.104859_b39","doi-asserted-by":"crossref","unstructured":"Wu, B., Wan, A., Yue, X., Keutzer, K., 2018. Squeezeseg: Convolutional neural nets with recurrent crf for real-time road-object segmentation from 3d lidar point cloud. In: International Conference on Robotics and Automation. pp. 1887\u20131893.","DOI":"10.1109\/ICRA.2018.8462926"},{"key":"10.1016\/j.cviu.2026.104859_b40","doi-asserted-by":"crossref","unstructured":"Wu, B., Zhou, X., Zhao, S., Yue, X., Keutzer, K., 2019. Squeezesegv2: Improved model structure and unsupervised domain adaptation for road-object segmentation from a lidar point cloud. In: International Conference on Robotics and Automation. pp. 4376\u20134382.","DOI":"10.1109\/ICRA.2019.8793495"},{"key":"10.1016\/j.cviu.2026.104859_b41","first-page":"11035","article-title":"PolarMix: A general data augmentation technique for LiDAR point clouds","volume":"vol. 35","author":"Xiao","year":"2022"},{"key":"10.1016\/j.cviu.2026.104859_b42","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"vol. 34","author":"Xie","year":"2021"},{"key":"10.1016\/j.cviu.2026.104859_b43","doi-asserted-by":"crossref","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. In: European Conference on Computer Vision. pp. 1\u201319.","DOI":"10.1007\/978-3-030-58604-1_1"},{"key":"10.1016\/j.cviu.2026.104859_b44","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Bai, L., Huang, X., 2021. FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding. In: International Conference on Intelligent Robots and Systems. pp. 4453\u20134458.","DOI":"10.1109\/IROS51168.2021.9636385"},{"key":"10.1016\/j.cviu.2026.104859_b45","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P., Koltun, V., 2021. Point Transformer. In: International Conference on Computer Vision. pp. 16239\u201316248.","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"10.1016\/j.cviu.2026.104859_b46","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110532","article-title":"Advancements in point cloud data augmentation for deep learning: A survey","volume":"153","author":"Zhu","year":"2024","journal-title":"Pattern Recognit.","ISSN":"https:\/\/id.crossref.org\/issn\/0031-3203","issn-type":"print"},{"key":"10.1016\/j.cviu.2026.104859_b47","doi-asserted-by":"crossref","unstructured":"Zhu, X., Zhou, H., Wang, T., Hong, F., Ma, Y., Li, W., Li, H., Lin, D., 2021a. Cylindrical and asymmetrical 3d convolution networks for lidar segmentation. In: Computer Vision and Pattern Recognition. pp. 9939\u20139948.","DOI":"10.1109\/CVPR46437.2021.00981"},{"key":"10.1016\/j.cviu.2026.104859_b48","doi-asserted-by":"crossref","unstructured":"Zhu, X., Zhou, H., Wang, T., Hong, F., Ma, Y., Li, W., Li, H., Lin, D., 2021b. Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation. In: Computer Vision and Pattern Recognition. pp. 9934\u20139943.","DOI":"10.1109\/CVPR46437.2021.00981"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226002262?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226002262?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T03:43:34Z","timestamp":1783223014000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226002262"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":48,"alternative-id":["S1077314226002262"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104859","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Trainable pointwise decoder module and virtual range image-guided copy-rotate-paste augmentation for point cloud segmentation","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104859","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"104859"}}