Relation-aware place recognition network for large-scale point clouds

Wen HAO; Wenjing ZHANG; Yan LV; Li GUO

doi:10.1631/ENG.ITEE.2025.0170

Your Location：

Home >

Browse articles >

Relation-aware place recognition network for large-scale point clouds

Regular Papers | Updated：2026-10-08

- Relation-aware place recognition network for large-scale point clouds
- Relation-aware place recognition network for large-scale point clouds
- ENGINEERING Information Technology & Electronic Engineering Vol. 27, Issue 9, (2026)
- Affiliations：
  
  Department of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048, China
  Shaanxi Key Laboratory for Network Computing and Security Technology, Xi’an 710048, China
  Department of Computing and Mathematics, Manchester Metropolitan University, Manchester M15 6BX, UK
- Author bio：
  
  ✉Wen HAO, haowensxsf@163.com
- Funds：
- DOI：10.1631/ENG.ITEE.2025.0170
  CLC： TP391
- Received：08 December 2025，
  
  Revised：2026-07-17，
  
  Published：01 September 2026
- Accepted：
Scan QR Code
Wen HAO, Wenjing ZHANG, Yan LV, et al. Relation-aware place recognition network for large-scale point clouds[J]. ENGINEERING Information Technology & Electronic Engineering, 2026, 27(9): 250170-11.
DOI：

Wen HAO, Wenjing ZHANG, Yan LV, et al. Relation-aware place recognition network for large-scale point clouds[J]. ENGINEERING Information Technology & Electronic Engineering, 2026, 27(9): 250170-11. DOI： 10.1631/ENG.ITEE.2025.0170.

摘要

Abstract

Most existing point cloud-based place recognition methods emphasize feature extraction from individual points or local regions

while largely neglecting the relational information embedded within local neighborhoods. As a result

they often fail to capture discriminative relational patterns

leading to reduced recognition accuracy in scenes containing geometrically similar structures. In this paper

we propose a novel relation-aware network (RA-Net) for place recognition. RA-Net jointly exploits local relational cues and global contextual information to learn discriminative scene representations for large-scale point cloud-based place recognition. First

a spatial relation feature extraction (SRFE) module is proposed to exploit relational information embedded within local neighborhoods. By learning relation-aware weights and adaptively aggregating neighborhood information

the proposed module captures discriminative relational patterns by jointly considering feature discrepancies and spatial offsets. Furthermore

a global feature extraction (GFE) module is introduced to aggregate global feature statistics and integrate them with pointwise representations

enabling local features to be enhanced with global contextual cues. Experimental results on four benchmark datasets demonstrate that RA-Net can generate more discriminative global descriptors and achieve promising performance. It exhibits strong generalization capabilities for unseen scenes.

关键词

Keywords

references

Arandjelovic R , Gronat P , Torii A , et al. , 2016 . NetVLAD: CNN architecture for weakly supervised place recognition . Proc IEEE Conf on Computer Vision and Pattern Recognition , p. 5297 - 5307 . https://doi.org/10.1109/CVPR.2016.572 https://doi.org/10.1109/CVPR.2016.572

Cattaneo D , Vaghi M , Valada A , 2022 . LCDNet: deep loop closure detection and point cloud registration for LiDAR SLAM . IEEE Trans Robot , 38 ( 4 ): 2074 - 2093 . https://doi.org/10.1109/TRO.2022.3150683 https://doi.org/10.1109/TRO.2022.3150683

Chen LN , Wang H , Kong H , et al. , 2023 . Point-wise transformer with sparse convolution network for place recognition . IEEE Robot Autom Lett , 8 ( 6 ): 3414 - 3421 . https://doi.org/10.1109/LRA.2023.3267693 https://doi.org/10.1109/LRA.2023.3267693

Du J , Wang R , Cremers D , 2020 . DH3D: deep hierarchical 3D descriptors for robust large-scale 6DoF relocalization . 16 th European Conf on Computer Vision , p. 744 - 762 . https://doi.org/10.1007/978-3-030-58548-8_43 https://doi.org/10.1007/978-3-030-58548-8_43

Fan ZX , Song ZB , Liu HY , et al. , 2022 . SVT-Net: super light-weight sparse voxel transformer for large scale place recognition . Proc 36 th AAAI Conf on Artificial Intelligence , p. 551 - 560 . https://doi.org/10.1609/aaai.v36i1.19934 https://doi.org/10.1609/aaai.v36i1.19934

Griffiths E , Haghighat M , Denman S , et al. , 2025 . HOTFormerLoc: hierarchical octree transformer for versatile LiDAR place recognition across ground and aerial views . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 6648 - 6658 . https://doi.org/10.1109/cvpr52734.2025.00623 https://doi.org/10.1109/cvpr52734.2025.00623

Hao W , Zhang WJ , Jin HY , 2024 . SAGE-Net: employing spatial attention and geometric encoding for point cloud based place recognition . IEEE Robot Autom Lett , 9 ( 6 ): 4958 - 4965 . https://doi.org/10.1109/LRA.2024.3387112 https://doi.org/10.1109/LRA.2024.3387112

He L , Wang XL , Zhang H , 2016 . M2DP: a novel 3D point cloud descriptor and its application in loop closure detection . IEEE/RSJ Int Conf on Intelligent Robots and Systems , p. 231 - 237 . https://doi.org/10.1109/iros.2016.7759060 https://doi.org/10.1109/iros.2016.7759060

Hou ZX , Yan Y , Xu CZ , et al. , 2022 . HiTPR: hierarchical transformer for place recognition in point cloud . Int Conf on Robotics and Automation , p. 2612 - 2618 . https://doi.org/10.1109/icra46639.2022.9811737 https://doi.org/10.1109/icra46639.2022.9811737

Hui L , Cheng MM , Xie J , et al. , 2022 . Efficient 3D point cloud feature learning for large-scale place recognition . IEEE Trans Image Process , 31 : 1258 - 1270 . https://doi.org/10.1109/TIP.2021.3136714 https://doi.org/10.1109/TIP.2021.3136714

Kim G , Kim A , 2018 . Scan context: egocentric spatial descriptor for place recognition within 3D point cloud map . IEEE/RSJ Int Conf on Intelligent Robots and Systems , p. 4802 - 4809 . https://doi.org/10.1109/iros.2018.8593953 https://doi.org/10.1109/iros.2018.8593953

Komorowski J , 2021 . MinkLoc3D: point cloud based large-scale place recognition . Proc IEEE Winter Conf on Applications of Computer Vision , p. 1789 - 1798 . https://doi.org/10.1109/wacv48630.2021.00183 https://doi.org/10.1109/wacv48630.2021.00183

Komorowski J , 2022 . Improving point cloud based place recognition with ranking-based loss and large batch training . 26 th Int Conf on Pattern Recognition , p. 3699 - 3705 . https://doi.org/10.1109/icpr56361.2022.9956458 https://doi.org/10.1109/icpr56361.2022.9956458

Komorowski J , Wysoczańska M , Trzcinski T , 2021 . MinkLoc++: LiDAR and monocular image fusion for place recognition . Int Joint Conf on Neural Networks , p. 1 - 8 . https://doi.org/10.1109/ijcnn52387.2021.9533373 https://doi.org/10.1109/ijcnn52387.2021.9533373

Komorowski J , Wysoczańska M , Trzcinski T , 2022 . EgoNN: egocentric neural network for point cloud based 6DoF relocalization at the city scale . IEEE Robot Autom Lett , 7 ( 2 ): 722 - 729 . https://doi.org/10.1109/LRA.2021.3133593 https://doi.org/10.1109/LRA.2021.3133593

Kong D , Li X , Ni PZ , et al. , 2024 . TopSPR-Net: topology aware segment-level point cloud learning descriptors for three-dimensional place recognition in large-scale environments . IEEE Trans Ind Electron , 71 ( 10 ): 13406 - 13416 . https://doi.org/10.1109/TIE.2024.3363747 https://doi.org/10.1109/TIE.2024.3363747

Kong X , Yang XM , Zhai GY , et al. , 2020 . Semantic graph based place recognition for 3D point clouds . IEEE/RSJ Int Conf on Intelligent Robots and Systems , p. 8216 - 8223 . https://doi.org/10.1109/iros45743.2020.9341060 https://doi.org/10.1109/iros45743.2020.9341060

Li QP , Zhuang Y , Huai JZ , et al. , 2024 . An efficient point cloud place recognition approach based on transformer in dynamic environment . ISPRS J Photogramm Remote Sens , 207 : 14 - 26 . https://doi.org/10.1016/j.isprsjprs.2023.11.013 https://doi.org/10.1016/j.isprsjprs.2023.11.013

Liu CX , Chen GY , Song R , 2024 . LPS-Net: lightweight parameter-shared network for point cloud-based place recognition . IEEE Int Conf on Robotics and Automation , p. 448 - 454 . https://doi.org/10.1109/icra57147.2024.10610758 https://doi.org/10.1109/icra57147.2024.10610758

Liu Z , Zhou SB , Suo CZ , et al. , 2019 . LPD-Net: 3D point cloud learning for large-scale place recognition and environment analysis . Proc IEEE/CVF Int Conf on Computer Vision , p. 2831 - 2840 . https://doi.org/10.1109/ICCV.2019.00292 https://doi.org/10.1109/ICCV.2019.00292

Lu T , Wang LM , Wu GS , 2021 . CGA-Net: category guided aggregation for point cloud semantic segmentation . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 11688 - 11697 . https://doi.org/10.1109/cvpr46437.2021.01152 https://doi.org/10.1109/cvpr46437.2021.01152

Ma JY , Zhang J , Xu JT , et al. , 2022 . OverlapTransformer: an efficient and yaw-angle-invariant transformer network for LiDAR-based place recognition . IEEE Robot Autom Lett , 7 ( 3 ): 6958 - 6965 . https://doi.org/10.1109/LRA.2022.3178797 https://doi.org/10.1109/LRA.2022.3178797

Ma JY , Xiong GM , Xu JY , et al. , 2024 . CVTNet: a cross-view transformer network for LiDAR-based place recognition in autonomous driving environments . IEEE Trans Ind Inform , 20 ( 3 ): 4039 - 4048 . https://doi.org/10.1109/TII.2023.3313635 https://doi.org/10.1109/TII.2023.3313635

Maddern W , Pascoe G , Linegar C , et al. , 2017 . 1 year, 1000 km: the Oxford RobotCar dataset . Int J Robot Res , 36 ( 1 ): 3 - 15 . https://doi.org/10.1177/0278364916679498 https://doi.org/10.1177/0278364916679498

Miao Y , Engelmann F , Vysotska O , et al. , 2025 . SceneGraphLoc: cross-modal coarse visual localization on 3D scene graphs . 18 th European Conf on Computer Vision , p. 127 - 150 . https://doi.org/10.1007/978-3-031-73242-3_8 https://doi.org/10.1007/978-3-031-73242-3_8

Qi CR , Su H , Mo K , et al. , 2017 . PointNet: deep learning on point sets for 3D classification and segmentation . Proc IEEE Conf on Computer Vision and Pattern Recognition , p. 77 - 85 . https://doi.org/10.1109/CVPR.2017.16 https://doi.org/10.1109/CVPR.2017.16

Rizzini DL , 2017 . Place recognition of 3D landmarks based on geometric relations . IEEE/RSJ Int Conf on Intelligent Robots and Systems , p. 648 - 654 . https://doi.org/10.1109/iros.2017.8202220 https://doi.org/10.1109/iros.2017.8202220

Röhling T , Mack J , Schulz D , 2015 . A fast histogram-based similarity measure for detecting loop closures in 3-D LIDAR data . IEEE/RSJ Int Conf on Intelligent Robots and Systems , p. 736 - 741 . https://doi.org/10.1109/iros.2015.7353454 https://doi.org/10.1109/iros.2015.7353454

Rosinol A , Gupta A , Abate M , et al. , 2020 . 3D dynamic scene graphs: actionable spatial perception with places, objects, and humans . https://arxiv.org/abs/2002.06289 https://arxiv.org/abs/2002.06289

Shu DW , Kwon J , 2024 . Hierarchical bidirected graph convolutions for large-scale 3-D point cloud place recognition . IEEE Trans Neur Netw Learn Syst , 35 ( 7 ): 9651 - 9662 . https://doi.org/10.1109/tnnls.2023.3236313 https://doi.org/10.1109/tnnls.2023.3236313

Siva S , Nahman Z , Zhang H , 2020 . Voxel-based representation learning for place recognition based on 3D point clouds . IEEE/RSJ Int Conf on Intelligent Robots and Systems , p. 8351 - 8357 . https://doi.org/10.1109/IROS45743.2020.9340992 https://doi.org/10.1109/IROS45743.2020.9340992

Sun Q , Liu HY , He J , et al. , 2020 . DAGC: employing dual attention and graph convolution for point cloud based place recognition . Proc Int Conf on Multimedia Retrieval , p. 224 - 232 . https://doi.org/10.1145/3372278.3390693 https://doi.org/10.1145/3372278.3390693

Tang WJ , Yang CG , An ZL , et al. , 2026 . EfficientVPR: toward efficient visual place recognition via scene-aware prompt tuning and adaptive feature enhancement . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 33738 - 33748 .

Uy MA , Lee GH , 2018 . PointNetVLAD: deep point cloud based retrieval for large-scale place recognition . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 4470 - 4479 . https://doi.org/10.1109/CVPR.2018.00470 https://doi.org/10.1109/CVPR.2018.00470

Vidanapathirana K , Ramezani M , Moghadam P , et al. , 2022 . LoGG3D-Net: locally guided global descriptor learning for 3D place recognition . Int Conf on Robotics and Automation , p. 2215 - 2221 . https://doi.org/10.1109/ICRA46639.2022.9811753 https://doi.org/10.1109/ICRA46639.2022.9811753

Wen CC , Huang H , Liu YS , 2023 . Pyramid learnable tokens for 3D LiDAR place recognition . IEEE Int Conf on Robotics and Automation , p. 4143 - 4149 . https://doi.org/10.1109/icra48891.2023.10161523 https://doi.org/10.1109/icra48891.2023.10161523

Xia Y , Xu YS , Li S , et al. , 2021 . SOE-Net: a self-attention and orientation encoding network for point cloud based place recognition . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 11343 - 11352 . https://doi.org/10.1109/cvpr46437.2021.01119 https://doi.org/10.1109/cvpr46437.2021.01119

Xia Y , Gladkova M , Wang R , et al. , 2022 . PVT3D: point voxel transformers for place recognition from sparse LiDAR scans . https://arxiv.org/pdf/2211.12542v1 https://arxiv.org/pdf/2211.12542v1

Xia Y , Gladkova M , Wang R , et al. , 2023 . CASSPR: cross attention single scan place recognition . Proc IEEE/CVF Int Conf on Computer Vision , p. 8427 - 8438 . https://doi.org/10.1109/iccv51070.2023.00777 https://doi.org/10.1109/iccv51070.2023.00777

Zhang WX , Xiao CX , 2019 . PCAN: 3D attention map learning using contextual information for point cloud based retrieval . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 12428 - 12437 . https://doi.org/10.1109/CVPR.2019.01272 https://doi.org/10.1109/CVPR.2019.01272

Zhang YJ , Shi PC , Li JY , 2024 . LiDAR-based place recognition for autonomous driving: a survey . ACM Comput Surv , 57 ( 4 ): 106 . https://doi.org/10.1145/3707446 https://doi.org/10.1145/3707446

Zuo WL , Liu LG , Li YZ , et al. , 2025 . PRGS: patch-to-region graph search for visual place recognition . Pattern Recogn , 166 : 111673 . https://doi.org/10.1016/j.patcog.2025.111673 https://doi.org/10.1016/j.patcog.2025.111673

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

SmartPaint: a co-creative drawing system based on generative adversarial networks

Social radar Doppler: multi-scenario validation ofsocial media-based crisis early warning

Decoupled prompt-guided mixture-of-experts dynamic distillation for multimodal recommendation

Dynamic trend perception for fine-grained unmanned aerial vehicle anomaly detection in flight data

Adaptive practical fixed-time tracking control with prescribed performance for robotic manipulators

Related Author

Pei CHEN

Wei XIANG

Peng CHEN

Wei-yue GAO

Ke-jun ZHANG

Lingyun SUN

Meng Yi

Zhongjian Hu

Related Institution

State Key Lab of CAD & CG, Zhejiang University

Alibaba-Zhejiang University Joint Institute of Frontier Technologies

Key Laboratory of Design Intelligence and Digital Creativity of Zhejiang Province

Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast University

School of Computer Science and Engineering, Southeast University

Chat

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰