{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T07:05:10Z","timestamp":1779692710720,"version":"3.53.1"},"reference-count":65,"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":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.neunet.2026.108767","type":"journal-article","created":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T23:08:25Z","timestamp":1771801705000},"page":"108767","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["From sparse semantics to rich instances: Empowering label-efficient LiDAR panoptic segmentation via geometric priors"],"prefix":"10.1016","volume":"200","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5406-1011","authenticated-orcid":false,"given":"Weijian","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9867-836X","authenticated-orcid":false,"given":"Haichuan","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3041-4697","authenticated-orcid":false,"given":"Zhizhong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9346-1196","authenticated-orcid":false,"given":"Xin","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1653-4341","authenticated-orcid":false,"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6945-7437","authenticated-orcid":false,"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108767_bib0001","series-title":"Point cloud labeler","author":"Behley","year":"2019"},{"key":"10.1016\/j.neunet.2026.108767_bib0002","series-title":"RCRA","first-page":"13596","article-title":"A benchmark for liDAR-based panoptic segmentation based on KITTI","author":"Behley","year":"2021"},{"key":"10.1016\/j.neunet.2026.108767_bib0003","series-title":"CVPR","first-page":"4413","article-title":"The Lov\u00e1sz-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks","author":"Berman","year":"2018"},{"key":"10.1016\/j.neunet.2026.108767_bib0004","unstructured":"Caine, B., Roelofs, R., Vasudevan, V., Ngiam, J., Chai, Y., Chen, Z., & Shlens, J. (2021). Pseudo-labeling for scalable 3D object detection. arXiv: 2103.02093."},{"key":"10.1016\/j.neunet.2026.108767_bib0005","doi-asserted-by":"crossref","unstructured":"\u00c7anak\u00e7\u0131, A. S., V\u00f6disch, N., Petek, K., Burgard, W., & Valada, A. (2025). Label-efficient LiDAR panoptic segmentation. arXiv: 2503.02372.","DOI":"10.1109\/IROS60139.2025.11245657"},{"key":"10.1016\/j.neunet.2026.108767_bib0006","series-title":"ECCV","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.neunet.2026.108767_bib0007","series-title":"AAAI","first-page":"1140","article-title":"SSPC-Net: Semi-supervised semantic 3D point cloud segmentation network","author":"Cheng","year":"2021"},{"key":"10.1016\/j.neunet.2026.108767_bib0008","unstructured":"Chibane, J., Engelmann, F., Tran, T. A., & Pons-Moll, G. (2022). Semantic instance segmentation of 3D scenes through weak bounding box supervision. arXiv: 2206.01203."},{"key":"10.1016\/j.neunet.2026.108767_bib0009","series-title":"CVPR","first-page":"1100","article-title":"Twist: Two-way inter-label self-training for semi-supervised 3D instance segmentation","author":"Chu","year":"2022"},{"key":"10.1016\/j.neunet.2026.108767_bib0010","unstructured":"Dong, S., Li, R., Wei, J., Liu, F., & Lin, G. (2022). RWSeg: Cross-graph competing random walks for weakly supervised 3D instance segmentation. arXiv: 2208.05110."},{"key":"10.1016\/j.neunet.2026.108767_bib0011","series-title":"ACM SIGKDD conference on knowledge discovery and data mining (KDD)","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","author":"Ester","year":"1996"},{"key":"10.1016\/j.neunet.2026.108767_bib0012","first-page":"3795","article-title":"Panoptic nuscenes: A large-scale benchmark for LiDar panoptic segmentation and tracking","volume":"7","author":"Fong","year":"2022","journal-title":"RAL"},{"key":"10.1016\/j.neunet.2026.108767_bib0013","first-page":"3216","article-title":"Panoster: End-to-end panoptic segmentation of LiDAR point clouds","volume":"6","author":"Gasperini","year":"2021","journal-title":"RAL"},{"key":"10.1016\/j.neunet.2026.108767_bib0014","series-title":"CVPR","first-page":"3354","article-title":"Are we ready for autonomous driving? The KITTI vision benchmark suite","author":"Geiger","year":"2012"},{"key":"10.1016\/j.neunet.2026.108767_bib0015","series-title":"CVPR","first-page":"13090","article-title":"LiDAR-based panoptic segmentation via dynamic shifting network","author":"Hong","year":"2021"},{"key":"10.1016\/j.neunet.2026.108767_bib0016","series-title":"CVPR","first-page":"15587","article-title":"Exploring data-efficient 3D scene understanding with contrastive scene contexts","author":"Hou","year":"2021"},{"issue":"8","key":"10.1016\/j.neunet.2026.108767_bib0017","doi-asserted-by":"crossref","first-page":"2070","DOI":"10.1007\/s11263-023-01799-6","article-title":"Improving semi-supervised and domain-adaptive semantic segmentation with self-supervised depth estimation","volume":"131","author":"Hoyer","year":"2023","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.108767_bib0018","series-title":"ECCV","first-page":"600","article-title":"SQN: Weakly-supervised semantic segmentation of large-scale 3D point clouds","author":"Hu","year":"2022"},{"key":"10.1016\/j.neunet.2026.108767_bib0019","series-title":"ECCV","first-page":"248","article-title":"Lidal: Inter-frame uncertainty based active learning for 3D LiDAR semantic segmentation","author":"Hu","year":"2022"},{"key":"10.1016\/j.neunet.2026.108767_bib0020","unstructured":"Hurtado, J. V., Mohan, R., Burgard, W., & Valada, A. (2020). MOPT: Multi-object panoptic tracking. arXiv: 2004.08189."},{"key":"10.1016\/j.neunet.2026.108767_bib0021","unstructured":"Jiang, W., Zhang, J., Wang, D., Zhang, Q., Wang, Z., & Du, B. (2024). Lemevit: Efficient vision transformer with learnable meta tokens for remote sensing image interpretation. arXiv: 2405.09789."},{"key":"10.1016\/j.neunet.2026.108767_bib0022","series-title":"CVPR","first-page":"21705","article-title":"Lasermix for semi-supervised LiDAR semantic segmentation","author":"Kong","year":"2023"},{"key":"10.1016\/j.neunet.2026.108767_bib0023","series-title":"ICRA","first-page":"9207","article-title":"SMAC-Seg: LiDAR panoptic segmentation via sparse multi-directional attention clustering","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2026.108767_bib0024","series-title":"ICRA","first-page":"8239","article-title":"CPSeg: Cluster-free panoptic segmentation of 3D LiDAR point clouds","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2026.108767_bib0025","series-title":"CVPR","first-page":"11809","article-title":"Panoptic-PHNet: Towards real-time and high-precision LiDAR panoptic segmentation via clustering pseudo heatmap","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2026.108767_bib0026","series-title":"CVPR","first-page":"14930","article-title":"HybridCR: Weakly-supervised 3D point cloud semantic segmentation via hybrid contrastive regularization","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2026.108767_bib0027","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"23344","article-title":"Improving generalized zero-shot learning by exploring the diverse semantics from external class names","author":"Li","year":"2024"},{"key":"10.1016\/j.neunet.2026.108767_bib0028","series-title":"CVPR","first-page":"8428","article-title":"SS3D: Sparsely-supervised 3D object detection from point cloud","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2026.108767_bib0029","doi-asserted-by":"crossref","first-page":"938","DOI":"10.1007\/s11263-022-01740-3","article-title":"RM3D: Robust data-efficient 3D scene parsing via traditional and learnt 3D descriptors-based semantic region merging","volume":"131","author":"Liu","year":"2023","journal-title":"IJCV"},{"key":"10.1016\/j.neunet.2026.108767_bib0030","series-title":"ECCV","first-page":"37","article-title":"Weakly supervised 3D scene segmentation with region-level boundary awareness and instance discrimination","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2026.108767_bib0031","series-title":"ECCV","first-page":"70","article-title":"Less: Label-efficient semantic segmentation for LiDAR point clouds","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2026.108767_bib0032","series-title":"CVPR","first-page":"1726","article-title":"One thing one click: A self-training approach for weakly supervised 3D Semantic segmentation","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2026.108767_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107673","article-title":"LaTP: LiDAR-aided multimodal token pruning for efficient trajectory prediction of autonomous driving","volume":"190","author":"Lu","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108767_bib0034","first-page":"4454","article-title":"Towards a weakly supervised framework for 3D point cloud object detection and annotation","volume":"44","author":"Meng","year":"2021","journal-title":"TPAMI"},{"key":"10.1016\/j.neunet.2026.108767_bib0035","series-title":"ECCV","first-page":"515","article-title":"Weakly supervised 3D object detection from LiDAR point cloud","author":"Meng","year":"2020"},{"key":"10.1016\/j.neunet.2026.108767_bib0036","series-title":"CVPR","first-page":"5217","article-title":"Temporal consistent 3D LiDAR representation learning for semantic perception in autonomous driving","author":"Nunes","year":"2023"},{"key":"10.1016\/j.neunet.2026.108767_bib0037","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107332","article-title":"Attribute-guided feature fusion network with knowledge-inspired attention mechanism for multi-source remote sensing classification","volume":"187","author":"Pan","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108767_bib0038","series-title":"CVPR","first-page":"8277","article-title":"Seamless scene segmentation","author":"Porzi","year":"2019"},{"key":"10.1016\/j.neunet.2026.108767_bib0039","series-title":"CVPR","first-page":"16076","article-title":"GP-S3Net: Graph-based panoptic sparse semantic segmentation network","author":"Razani","year":"2021"},{"key":"10.1016\/j.neunet.2026.108767_bib0040","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3093","article-title":"Token contrast for weakly-supervised semantic segmentation","author":"Ru","year":"2023"},{"key":"10.1016\/j.neunet.2026.108767_bib0041","doi-asserted-by":"crossref","unstructured":"Shao, Z., Cheng, Y., Li, F., Zhou, Y., Lu, X., Xie, Y., & Ma, L. (2025a). MOL: Joint estimation of micro-expression, optical flow, and landmark via transformer-graph-style convolution. arXiv: 2506.14511.","DOI":"10.1109\/TPAMI.2025.3581162"},{"issue":"4","key":"10.1016\/j.neunet.2026.108767_bib0042","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.1007\/s11263-024-02258-6","article-title":"Facial action unit detection by adaptively constraining self-attention and causally deconfounding sample","volume":"133","author":"Shao","year":"2025","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.108767_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107704","article-title":"PolarFusion: A multi-modal fusion algorithm for 3D object detection based on polar coordinates","volume":"190","author":"Shi","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108767_bib0044","unstructured":"Shi, X., Xu, X., Chen, K., Cai, L., Foo, C. S., & Jia, K. (2021). Label-efficient point cloud semantic segmentation: An active learning approach. arXiv: 2101.06931."},{"key":"10.1016\/j.neunet.2026.108767_bib0045","doi-asserted-by":"crossref","first-page":"1894","DOI":"10.1109\/TRO.2021.3122069","article-title":"EfficientLPS: Efficient LiDAR panoptic segmentation","volume":"38","author":"Sirohi","year":"2021","journal-title":"IEEE Transactions on Robotics (T-RO)"},{"key":"10.1016\/j.neunet.2026.108767_bib0046","series-title":"AAAI","first-page":"2339","article-title":"Pups: Point cloud unified panoptic segmentation","author":"Su","year":"2023"},{"key":"10.1016\/j.neunet.2026.108767_bib0047","doi-asserted-by":"crossref","first-page":"1838","DOI":"10.1109\/TIP.2024.3372449","article-title":"Image understands point cloud: Weakly supervised 3D semantic segmentation via association learning","volume":"33","author":"Sun","year":"2024","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.108767_bib0048","first-page":"4952","article-title":"SegGroup: Seg-level supervision for 3D instance and semantic segmentation","volume":"31","author":"Tao","year":"2022","journal-title":"TIP"},{"key":"10.1016\/j.neunet.2026.108767_bib0049","series-title":"CVPR","first-page":"2697","article-title":"Scribble-supervised LiDAR semantic segmentation","author":"Unal","year":"2022"},{"key":"10.1016\/j.neunet.2026.108767_bib0050","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.neunet.2020.12.001","article-title":"Modular deep reinforcement learning from reward and punishment for robot navigation","volume":"135","author":"Wang","year":"2021","journal-title":"Neural Networks"},{"issue":"6","key":"10.1016\/j.neunet.2026.108767_bib0051","doi-asserted-by":"crossref","first-page":"10043","DOI":"10.1109\/TNNLS.2025.3543620","article-title":"SDSimPoint: Shallow-deep similarity learning for few-shot point cloud semantic segmentation","volume":"36","author":"Wang","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.108767_bib0052","series-title":"ICRA","first-page":"4348","article-title":"FGR: Frustum-aware geometric reasoning for weakly supervised 3D vehicle detection","author":"Wei","year":"2021"},{"key":"10.1016\/j.neunet.2026.108767_bib0053","series-title":"CVPR","first-page":"5251","article-title":"Spatiotemporal self-supervised learning for point clouds in the wild","author":"Wu","year":"2023"},{"key":"10.1016\/j.neunet.2026.108767_bib0054","first-page":"11035","article-title":"Polarmix: A general data augmentation technique for LiDAR point clouds","volume":"35","author":"Xiao","year":"2022","journal-title":"NIPS"},{"issue":"1","key":"10.1016\/j.neunet.2026.108767_bib0055","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1007\/s11263-024-02162-z","article-title":"Position-guided point cloud panoptic segmentation transformer","volume":"133","author":"Xiao","year":"2025","journal-title":"IJCV"},{"key":"10.1016\/j.neunet.2026.108767_bib0056","series-title":"CVPR","first-page":"13706","article-title":"Weakly supervised semantic point cloud segmentation: Towards 10x fewer labels","author":"Xu","year":"2020"},{"key":"10.1016\/j.neunet.2026.108767_bib0057","series-title":"CVPR","first-page":"8438","article-title":"Back to reality: Weakly-supervised 3D object detection with shape-guided label enhancement","author":"Xu","year":"2022"},{"key":"10.1016\/j.neunet.2026.108767_bib0058","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107503","article-title":"Enhancing realism in LiDAR scene generation with CSPA-DFN and linear cross-attention via diffusion transformer model","volume":"189","author":"Ye","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108767_bib0059","series-title":"CVPR","first-page":"1130","article-title":"Learning to detect mobile objects from LiDAR scans without labels","author":"You","year":"2022"},{"key":"10.1016\/j.neunet.2026.108767_bib0060","first-page":"1","article-title":"Cross-cloud consistency for weakly supervised point cloud semantic segmentation","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.108767_bib0061","series-title":"AAAI","first-page":"3421","article-title":"Weakly supervised semantic segmentation for large-scale point cloud","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neunet.2026.108767_bib0062","series-title":"CVPR","first-page":"15520","article-title":"Perturbed self-distillation: Weakly supervised large-scale point cloud semantic segmentation","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neunet.2026.108767_bib0063","series-title":"CVPR","first-page":"11079","article-title":"Sess: Self-ensembling semi-supervised 3D object detection","author":"Zhao","year":"2020"},{"key":"10.1016\/j.neunet.2026.108767_bib0064","series-title":"CVPR","first-page":"13194","article-title":"Panoptic-polarnet: Proposal-free lidar point cloud panoptic segmentation","author":"Zhou","year":"2021"},{"key":"10.1016\/j.neunet.2026.108767_bib0065","series-title":"CVPR","first-page":"9939","article-title":"Cylindrical and asymmetrical 3D convolution networks for LiDAR segmentation","author":"Zhu","year":"2021"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026002297?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026002297?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T06:38:10Z","timestamp":1779691090000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026002297"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":65,"alternative-id":["S0893608026002297"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108767","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"From sparse semantics to rich instances: Empowering label-efficient LiDAR panoptic segmentation via geometric priors","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108767","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"108767"}}