{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T12:52:34Z","timestamp":1781959954145,"version":"3.54.5"},"reference-count":27,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T00:00:00Z","timestamp":1771804800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306096"],"award-info":[{"award-number":["62306096"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471169"],"award-info":[{"award-number":["62471169"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LGEZ26F030001"],"award-info":[{"award-number":["LGEZ26F030001"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LY24F020015"],"award-info":[{"award-number":["LY24F020015"]}]},{"name":"National Science and Technology Innovation 2030 - Major Project","award":["2022ZD0208800"],"award-info":[{"award-number":["2022ZD0208800"]}]},{"name":"Central Government-Guided Local Science and Technology Development Fund","award":["2025ZY01045"],"award-info":[{"award-number":["2025ZY01045"]}]},{"name":"Zhejiang Provincial Key Laboratory of Brain Computer Collaborative Intelligence Technology and Applications","award":["2025E10015"],"award-info":[{"award-number":["2025E10015"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Scene flow, a key representation of motion information in 3D space, plays a critical role in numerous downstream tasks. However, existing point cloud scene flow estimation methods often experience significant performance degradation due to insufficient feature expressiveness or mismatching under sparse point cloud conditions. To alleviate these problems, we propose a novel dense structure distillation towards recurrent scene flow estimation method for sparse point clouds, significantly enhancing performance under low-density point cloud conditions through a dense structure distillation strategy. This module addresses the information loss caused by point cloud sparsity by leveraging high-quality point cloud features to effectively guide the learning of sparse point cloud feature extractors. To further refine the estimation results, a recurrent update strategy is adopted to gradually improve the accuracy and stability of scene flow estimation. Experimental results demonstrate that the proposed method achieves state-of-the-art performance on both the public FlyingThings3D and KITTI datasets, particularly under sparse point cloud conditions, and outperforms existing methods.<\/jats:p>","DOI":"10.1093\/comjnl\/bxag002","type":"journal-article","created":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T12:45:39Z","timestamp":1770900339000},"page":"945-953","source":"Crossref","is-referenced-by-count":0,"title":["Dense structure distillation towards recurrent scene flow estimation for sparse point cloud"],"prefix":"10.1093","volume":"69","author":[{"given":"Weichen","family":"Dai","sequence":"first","affiliation":[{"name":"Zhejiang Provincial Key Laboratory of Brain Computer Collaborative Intelligence Technology and Applications , Hangzhou Dianzi University, No. 1158, Ave. 2, Qiantang District, Hangzhou, 310018 Zhejiang,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyue","family":"Meng","sequence":"additional","affiliation":[{"name":"Zhejiang Provincial Key Laboratory of Brain Computer Collaborative Intelligence Technology and Applications , Hangzhou Dianzi University, No. 1158, Ave. 2, Qiantang District, Hangzhou, 310018 Zhejiang,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyang","family":"Weng","sequence":"additional","affiliation":[{"name":"Zhejiang Provincial Key Laboratory of Brain Computer Collaborative Intelligence Technology and Applications , Hangzhou Dianzi University, No. 1158, Ave. 2, Qiantang District, Hangzhou, 310018 Zhejiang,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhan","family":"Su","sequence":"additional","affiliation":[{"name":"Zhejiang Provincial Key Laboratory of Brain Computer Collaborative Intelligence Technology and Applications , Hangzhou Dianzi University, No. 1158, Ave. 2, Qiantang District, Hangzhou, 310018 Zhejiang,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"WanZeng","family":"Kong","sequence":"additional","affiliation":[{"name":"Zhejiang Provincial Key Laboratory of Brain Computer Collaborative Intelligence Technology and Applications , Hangzhou Dianzi University, No. 1158, Ave. 2, Qiantang District, Hangzhou, 310018 Zhejiang,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,2,23]]},"reference":[{"key":"2026062008162745700_ref1","first-page":"8375","article-title":"RAFT-3D: scene flow using rigid-motion embeddings","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Teed","year":"2021"},{"key":"2026062008162745700_ref2","first-page":"3254","article-title":"HPLFlowNet: hierarchical permutohedral lattice flownet for scene flow estimation on large-scale point clouds","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Xiuye","year":"2019"},{"key":"2026062008162745700_ref3","first-page":"529","article-title":"FlowNet3D: learning scene flow in 3D point clouds","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Liu","year":"2019"},{"key":"2026062008162745700_ref4","first-page":"10041","article-title":"Multi-scale bidirectional recurrent network with hybrid correlation for point cloud based scene flow estimation","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Cheng","year":"2023"},{"key":"2026062008162745700_ref5","first-page":"15109","article-title":"DifFlow3D: toward robust uncertainty-aware scene flow estimation with iterative diffusion-based refinement","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Liu","year":"2024"},{"key":"2026062008162745700_ref6","article-title":"GMSF: global matching scene flow","volume":"36","author":"Zhang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026062008162745700_ref7","first-page":"1266","article-title":"Learning to segment rigid motions from two frames","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Yang","year":"2021"},{"key":"2026062008162745700_ref8","doi-asserted-by":"crossref","first-page":"131508","DOI":"10.1016\/j.neucom.2025.131508","article-title":"PVFT-net: a point-voxel fusion method for self-supervised scene flow estimation with transformer","volume":"656","author":"Xiang","year":"2025","journal-title":"Neurocomputing"},{"key":"2026062008162745700_ref9","first-page":"668","article-title":"FlowFormer: a transformer architecture for optical flow","volume-title":"Proceedings of the European Conference on Computer Vision(ECCV)","author":"Huang","year":"2022"},{"key":"2026062008162745700_ref10","first-page":"16259","article-title":"Point transformer","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Zhao","year":"2021"},{"key":"2026062008162745700_ref11","first-page":"1","article-title":"Learning scene flow from 3D point clouds with cross-transformer and global motion cues","volume-title":"Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Zhai","year":"2023"},{"key":"2026062008162745700_ref12","doi-asserted-by":"crossref","first-page":"2566","DOI":"10.1109\/LRA.2023.3254431","article-title":"Pt-FlowNet: scene flow estimation on point clouds with point transformer","volume":"8","author":"Jingyun","year":"2023","journal-title":"IEEE Rob Autom Lett"},{"key":"2026062008162745700_ref13","doi-asserted-by":"crossref","first-page":"105368","DOI":"10.1016\/j.imavis.2024.105368","article-title":"Scene flow estimation from point cloud based on grouped relative self-attention","volume":"154","author":"Xiang","year":"2025","journal-title":"Image Vision Comput"},{"key":"2026062008162745700_ref14","first-page":"15491","article-title":"RadarDistill: boosting radar-based object detection performance via knowledge distillation from LiDAR features","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(CVPR)","author":"Bang","year":"2024"},{"key":"2026062008162745700_ref15","first-page":"21791","article-title":"PointDistiller: structured knowledge distillation towards efficient and compact 3d detection","volume-title":"Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhang","year":"2023"},{"key":"2026062008162745700_ref16","doi-asserted-by":"crossref","first-page":"2378","DOI":"10.1109\/TPAMI.2023.3330866","article-title":"Learning optical flow and scene flow with bidirectional camera-LiDAR fusion","volume":"46","author":"Liu","year":"2024","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2026062008162745700_ref17","first-page":"16901","article-title":"DELFlow: dense efficient learning of scene flow for large-scale point clouds","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Peng","year":"2023"},{"key":"2026062008162745700_ref18","doi-asserted-by":"crossref","first-page":"108684","DOI":"10.1016\/j.patcog.2022.108684","article-title":"Spatial information enhancement network for 3D object detection from point cloud","volume":"128","author":"Li","year":"2022","journal-title":"Pattern Recognit"},{"key":"2026062008162745700_ref19","doi-asserted-by":"crossref","first-page":"3107","DOI":"10.1093\/comjnl\/bxac153","article-title":"Chinese roberta distillation for emotion classification","volume":"66","author":"Liu","year":"2022","journal-title":"Comput J"},{"key":"2026062008162745700_ref20","first-page":"1","article-title":"Dynamic graph CNN for learning on point clouds","volume":"38","author":"Wang","year":"2019","journal-title":"ACM Trans Graph"},{"key":"2026062008162745700_ref25","doi-asserted-by":"publisher","first-page":"4040","DOI":"10.1109\/CVPR.2016.438","article-title":"A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Mayer","year":"2016"},{"key":"2026062008162745700_ref24","first-page":"5791","article-title":"CamLiFlow: bidirectional camera-LiDAR fusion for joint optical flow and scene flow estimation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Liu","year":"2022"},{"key":"2026062008162745700_ref26","doi-asserted-by":"publisher","first-page":"3061","DOI":"10.1109\/CVPR.2015.7298925","article-title":"Object scene flow for autonomous vehicles","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR)","author":"Menze","year":"2015"},{"key":"2026062008162745700_ref21","first-page":"527","article-title":"FLOT: scene flow on point clouds guided by optimal transport","volume-title":"Proceedings of the European Conference on Computer Vision(ECCV)","author":"Puy","year":"2020"},{"key":"2026062008162745700_ref22","first-page":"2805","article-title":"Occlusion guided scene flow estimation on 3D point clouds","author":"Ouyang","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops"},{"key":"2026062008162745700_ref23","doi-asserted-by":"crossref","first-page":"782","DOI":"10.1109\/3DV53792.2021.00087","article-title":"Occlusion guided self-supervised scene flow estimation on 3D point clouds","volume-title":"Proceedings of the 2021 International Conference on 3D Vision (3DV)","author":"Ouyang","year":"2021"},{"key":"2026062008162745700_ref27","first-page":"5271","article-title":"FlowMamba: learning point cloud scene flow with global motion propagation","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)","author":"Lin","year":"2025"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/69\/6\/945\/67076052\/bxag002.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/69\/6\/945\/67076052\/bxag002.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T12:16:39Z","timestamp":1781957799000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/69\/6\/945\/8495060"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,23]]},"references-count":27,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,2,23]]},"published-print":{"date-parts":[[2026,6,20]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxag002","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,6]]},"published":{"date-parts":[[2026,2,23]]}}}