{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:14:33Z","timestamp":1778285673814,"version":"3.51.4"},"reference-count":50,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T00:00:00Z","timestamp":1744675200000},"content-version":"vor","delay-in-days":104,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFF0304902"],"award-info":[{"award-number":["2020YFF0304902"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Image Processing"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Accurate point correspondences is critical for rigid point cloud registration in correspondence\u2010based methods. Many previous learning\u2010based methods employ encoder\u2010decoder backbone for point feature extraction, while applying attention mechanism for sparse superpoints to deal with the partial overlap situation. However, few of these methods focus on the intermediate layers yet mainly pay attention on the top\u2010most patch features, thus neglecting multi\u2010faceted feature perspectives leading to potential overlap areas estimation inaccuracy. Meanwhile, obtaining correct correspondences is usually interfered with the one\u2010to\u2010many case and outliers. To address these issues, we propose a multi\u2010level features extraction network with integrating linear dual attention mechanism into skip\u2010connection stage of encoder\u2010decoder backbone, both efficiently suppressing irrelevant information and guiding residual features to learn the common regions on which the network should focus to tackle the overlap estimation inaccuracy issue, combined with a parallel\u2010structured decoder forming distinguishable features and potential overlapping regions. Additionally, a two\u2010stage correspondences pruning process is designed to tackle the mismatch issue, which mainly depends on the rigid geometric constraint. Extensive experiments conducted on indoor and outdoor scene datasets demonstrate our method's accuracy and stability, by outperforming state\u2010of\u2010the\u2010art methods on registration\u00a0recall.<\/jats:p>","DOI":"10.1049\/ipr2.70055","type":"journal-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T09:12:48Z","timestamp":1748337168000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Integrating Linear Skip\u2010Attention With Transformer\u2010Based Network of Multi\u2010Level Features Extraction for Partial Point Cloud Registration"],"prefix":"10.1049","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6627-2134","authenticated-orcid":false,"given":"Qinyu","family":"He","sequence":"first","affiliation":[{"name":"Electronic Information School Wuhan University Hubei China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Sun","sequence":"additional","affiliation":[{"name":"Electronic Information School Wuhan University Hubei China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"265","published-online":{"date-parts":[[2025,4,15]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"crossref","unstructured":"S.Huang Z.Gojcic M.Usvyatsov A.Wieser andK.Schindler \u201cPREDATOR: Registration of 3D Point Clouds With Low Overlap \u201d inProceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2021) 4267\u20134276.","DOI":"10.1109\/CVPR46437.2021.00425"},{"key":"e_1_2_11_3_1","doi-asserted-by":"crossref","unstructured":"Z.Qin H.Yu C.Wang Y.Guo Y.Peng andK.Xu \u201cGeometric Transformer for Fast and Robust Point Cloud Registration \u201d inProceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2022) 11143\u201311152.","DOI":"10.1109\/CVPR52688.2022.01086"},{"key":"e_1_2_11_4_1","unstructured":"L.Zhu H.Guan C.Lin andR.Han \u201cLeveraging Inlier Correspondences Proportion for Point Cloud Registration \u201darXiv:2201.12094(2022)."},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3208380"},{"key":"e_1_2_11_6_1","doi-asserted-by":"crossref","unstructured":"H.Thomas C. R.Qi J. E.Deschaud B.Marcotegui F.Goulette andL. J.Guibas \u201cKPConv: Flexible and Deformable Convolution for Point Clouds \u201d inProceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV)(IEEE 2019) 6411\u20136420.","DOI":"10.1109\/ICCV.2019.00651"},{"key":"e_1_2_11_7_1","doi-asserted-by":"crossref","unstructured":"Z. J.YewandG. H.Lee \u201cRPM\u2010Net: Robust Point Matching Using Learned Features \u201d inProceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2020) 11824\u201311833.","DOI":"10.1109\/CVPR42600.2020.01184"},{"key":"e_1_2_11_8_1","doi-asserted-by":"crossref","unstructured":"H.Deng T.Birdal andS.Ilic \u201cPPF\u2010Foldnet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors \u201d inProceedings of the European Conference on Computer Vision(Springer 2018) 602\u2013618.","DOI":"10.1007\/978-3-030-01228-1_37"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3069848"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164093"},{"key":"e_1_2_11_11_1","doi-asserted-by":"crossref","unstructured":"Z.Chen K.Sun F.Yang andW.Tao \u201cSC2\u2010PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration \u201d inProceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2022) 13221\u201313231.","DOI":"10.1109\/CVPR52688.2022.01287"},{"key":"e_1_2_11_12_1","doi-asserted-by":"crossref","unstructured":"P. J.BeslandN. D.McKay \u201cMethod for Registration of 3\u2010D Shapes \u201dProceedings of SPIE 1611(1992):586\u2013606.","DOI":"10.1117\/12.57955"},{"key":"e_1_2_11_13_1","volume-title":"Linear Least\u2010Squares Optimization for Point\u2010to\u2010Plane ICP Surface Registration","author":"Low K. L.","year":"2004"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2009.V.021"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2513405"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2024.3417416"},{"key":"e_1_2_11_17_1","doi-asserted-by":"crossref","unstructured":"F.Tombari S.Salti andL.Di Stefano \u201cUnique Signatures of Histograms for Local Surface Description \u201d inProceedings of the European Conference on Computer Vision(Springer 2010) 356\u2013369.","DOI":"10.1007\/978-3-642-15558-1_26"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0627-y"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2007.02.009"},{"key":"e_1_2_11_20_1","doi-asserted-by":"crossref","unstructured":"R. B.Rusu N.Blodow andM.Beetz \u201cFast Point Feature Histograms (FPFH) for 3D Registration \u201d inProceedings of the 2009 IEEE International Conference on Robotics and Automation(IEEE 2009) 3212\u20133217.","DOI":"10.1109\/ROBOT.2009.5152473"},{"key":"e_1_2_11_21_1","doi-asserted-by":"crossref","unstructured":"C.Choy J.Park andV.Koltun \u201cFully Convolutional Geometric Features \u201d inProceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV)(IEEE 2019) 8958\u20138966.","DOI":"10.1109\/ICCV.2019.00905"},{"key":"e_1_2_11_22_1","doi-asserted-by":"crossref","unstructured":"S.Ao Q.Hu B.Yang A.Markham andY.Guo \u201cSpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration \u201d inProceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2021) 11753\u201311762.","DOI":"10.1109\/CVPR46437.2021.01158"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3312855"},{"key":"e_1_2_11_24_1","doi-asserted-by":"crossref","unstructured":"X.Bai Z.Luo L.Zhou H.Fu L.Quan andC. L.Tai \u201cD3Feat: Joint Learning of Dense Detection and Description of 3D Local Features \u201d inProceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2020) 6359\u20136367.","DOI":"10.1109\/CVPR42600.2020.00639"},{"key":"e_1_2_11_25_1","unstructured":"H.Yu F.Li M.Saleh B.Busam andS.Ilic \u201cCoFiNet: Reliable Coarse\u2010to\u2010Fine Correspondences for Robust PointCloud Registration \u201d inNIPS'21: Proceedings of the 35th International Conference on Neural Information Processing Systems(2021) 23872\u201323884."},{"key":"e_1_2_11_26_1","doi-asserted-by":"crossref","unstructured":"Z. J.YewandG. h.Lee \u201cREGTR: End\u2010to\u2010End Point Cloud Correspondences With Transformers \u201d inProceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2022) 6667\u20136676.","DOI":"10.1109\/CVPR52688.2022.00656"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1107\/S0567739476001873"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.88573"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3329578"},{"key":"e_1_2_11_30_1","doi-asserted-by":"crossref","unstructured":"J.Gao Q.Dong R.Wang et\u00a0al. \u201cOAAFormer: Robust and Efficient Point Cloud Registration Through Overlapping\u2010Aware Attention in Transformer \u201darXiv:2310.09817(2023).","DOI":"10.1007\/s11390-024-4165-6"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109876"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3237328"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3349199"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"e_1_2_11_35_1","doi-asserted-by":"crossref","unstructured":"X.Zhang J.Yang S.Zhang andY.Zhang \u201c3D Registration With Maximal Cliques \u201d inProceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2023) 17745\u201317754.","DOI":"10.1109\/CVPR52729.2023.01702"},{"key":"e_1_2_11_36_1","doi-asserted-by":"crossref","unstructured":"Y.WangandJ. M.Solomon \u201cDeep Closest Point: Learning Representations for Point Cloud Registration \u201d inProceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV)(IEEE 2019) 3523\u20133532.","DOI":"10.1109\/ICCV.2019.00362"},{"key":"e_1_2_11_37_1","doi-asserted-by":"crossref","unstructured":"G. D.Pais S.Ramalingam V. M.Govindu J. C.Nascimento R.Chellappa andP.Miraldo \u201c3DRegNet: A Deep Neural Network for 3D Point Registration \u201d inProceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2020) 7193\u20137203.","DOI":"10.1109\/CVPR42600.2020.00722"},{"key":"e_1_2_11_38_1","doi-asserted-by":"crossref","unstructured":"C.Choy W.Dong andV.Koltun \u201cDeep Global Registration \u201d inProceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2020) 2514\u20132523.","DOI":"10.1109\/CVPR42600.2020.00259"},{"key":"e_1_2_11_39_1","doi-asserted-by":"crossref","unstructured":"C.Choy J.Lee R.Ranftl J.Park andV.Koltun \u201cHigh\u2010Dimensional Convolutional Networks for Geometric Pattern Recognition \u201d inProceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2020) 11227\u201311236.","DOI":"10.1109\/CVPR42600.2020.01124"},{"key":"e_1_2_11_40_1","doi-asserted-by":"crossref","unstructured":"X.Bai Z.Luo L.Zhou et\u00a0al. \u201cPointDSC: Robust Point Cloud Registration Using Deep Spatial Consistency \u201d inProceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2021) 15859\u201315869.","DOI":"10.1109\/CVPR46437.2021.01560"},{"key":"e_1_2_11_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3476114"},{"key":"e_1_2_11_42_1","doi-asserted-by":"crossref","unstructured":"Y.Yuan Y.Wu X.Fan M.Gong Q.Miao andW.Ma \u201cInlier Confidence Calibration for Point Cloud Registration \u201d inProceedings of the 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2024) 5312\u20135321.","DOI":"10.1109\/CVPR52733.2024.00508"},{"key":"e_1_2_11_43_1","unstructured":"A.Katharopoulos A.Vyas N.Pappas andF.Fleuret \u201cTransformers are RNNs: Fast Autoregressive Transformers With Linear Attention \u201d inProceedings of the 37th International Conference on Machine Learning(PMLR 2020) 5156\u20135165."},{"key":"e_1_2_11_44_1","unstructured":"Q. Y.Zhou J.Park andV.Koltun \u201cOpen3D: A Modern Library for 3D Data Processing \u201darXiv:1801.09847(2018)."},{"key":"e_1_2_11_45_1","unstructured":"C. R.Qi H.Su K.Mo andL. J.Guibas \u201cPointnet: Deep Learning on Point Sets for 3D Classification and Segmentation \u201d in (IEEE 2017) 652\u2013660."},{"key":"e_1_2_11_46_1","doi-asserted-by":"crossref","unstructured":"A.Zeng S.Song M.Nie\u00dfner M.Fisher J.Xiao andT.Funkhouser \u201c3DMatch: Learning Local Geometric Descriptors From RGB\u2010D Reconstructions \u201d inProceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2017) 1802\u20131811.","DOI":"10.1109\/CVPR.2017.29"},{"key":"e_1_2_11_47_1","doi-asserted-by":"crossref","unstructured":"A.Geiger P.Lenz andR.Urtasun \u201cAre We Ready for Autonomous Driving? The Kitti Vision Benchmark Suite \u201d inProceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition(IEEE 2012) 3354\u20133361.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"e_1_2_11_48_1","doi-asserted-by":"crossref","unstructured":"V.Sarode A.Dhagat R. A.Srivatsan N.Zevallos S.Lucey andH.Choset \u201cMaskNet: A Fully\u2010Convolutional Network to Estimate Inlier Points \u201d inProceedings of the 2020 International Conference on 3D Vision (3DV)(IEEE 2020) 1029\u20131038.","DOI":"10.1109\/3DV50981.2020.00113"},{"key":"e_1_2_11_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3286943"},{"key":"e_1_2_11_50_1","doi-asserted-by":"crossref","unstructured":"H.Yu Z.Qin J.Hou et\u00a0al. \u201cRotation\u2010Invariant Transformer for Point Cloud Matching \u201d inProceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2023) 5384\u20135393.","DOI":"10.1109\/CVPR52729.2023.00521"},{"key":"e_1_2_11_51_1","doi-asserted-by":"crossref","unstructured":"F.Lu G.Chen Y.Liu et\u00a0al. \u201cHRegNet: A Hierarchical Network for Large\u2010Scale Outdoor LiDAR Point Cloud Registration \u201d inProceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV)(IEEE 2021) 16014\u201316023.","DOI":"10.1109\/ICCV48922.2021.01571"}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70055","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/ipr2.70055","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T23:44:42Z","timestamp":1778283882000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.70055"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1049\/ipr2.70055"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.70055","archive":["Portico"],"relation":{},"ISSN":["1751-9659","1751-9667"],"issn-type":[{"value":"1751-9659","type":"print"},{"value":"1751-9667","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2024-11-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70055"}}