点云融合技术综述：方法、应用与挑战

宋绍京; 李新建; 方非易

doi:10.12000/JR24236

点云融合技术综述：方法、应用与挑战

DOI: 10.12000/JR24236 CSTR: 32380.14.JR24236

1.
上海第二工业大学计算机与信息工程学院上海 201209
2.
上海第二工业大学智能制造与控制工程学院上海 201209

详细信息

作者简介:
宋绍京，博士，教授，主要研究方向为机器视觉、自动驾驶、光电信息处理等

李新建，硕士生，主要研究方向为自动驾驶、点云融合、3D目标检测等

方非易，博士，主要研究方向为图像分割、多模态机器学习、无人驾驶等

通讯作者:
方非易 fyfang@sspu.edu.cn

责任主编：陈育伟 Corresponding Editor: CHEN Yuwei
中图分类号: TN95
计量
- 文章访问数:
- HTML全文浏览量:
- PDF下载量:
- 被引次数: 0
出版历程
- 收稿日期: 2024-11-24
- 修回日期: 2025-06-03

A Review of Point Cloud Fusion Technology: Methods, Applications, and Challenges

1.
School of Computer and Information Engineering, Shanghai Polytechnic University, Shanghai 201209, China
2.
School of Intelligent Manufacturing and Control Engineering, Shanghai Polytechnic University, Shanghai 201209, China

More Information

Corresponding author: FANG Feiyi, fyfang@sspu.edu.cn

摘要

摘要: 点云融合技术作为3D (Three-Dimensional)数据处理的重要手段，在多个领域展现出巨大的潜力和应用前景。该文系统地综述了点云融合的基础概念、常用技术方法及其应用，深入分析了不同方法的发展现状和未来发展趋势。此外，该文还探讨了点云融合在自动驾驶、建筑和机器人等领域的实际应用及面临的挑战，尤其是在应对噪声、数据稀疏性和密度不均等问题时，如何在保证融合精度的同时平衡其复杂性。通过全面梳理现有研究进展，为未来点云融合技术的发展提供了有力参考，并为进一步提升融合算法的精度、鲁棒性和效率指明了可能的研究方向。
- 点云融合 /
- 3D数据处理 /
- 特征匹配 /
- 融合算法 /
- 深度学习
Abstract: As an important method of 3D (Three-Dimensional) data processing, point cloud fusion technology has shown great potential and promising applications in many fields. This paper systematically reviews the basic concepts, commonly used techniques, and applications of point cloud fusion and thoroughly analyzes the current status and future development trends of various fusion methods. Additionally, the paper explores the practical applications and challenges of point cloud fusion in fields such as autonomous driving, architecture, and robotics. Special attention is given to balancing algorithmic complexity with fusion accuracy, particularly in addressing issues like noise, data sparsity, and uneven point cloud density. This study serves as a strong reference for the future development of point cloud fusion technology by providing a comprehensive overview of the existing research progress and identifying possible research directions for further improving the accuracy, robustness, and efficiency of fusion algorithms.
- Point cloud fusion /
- 3D data processing /
- Feature matching /
- Fusion algorithm /
- Deep learning

HTML全文

图 1 点云数据表示

Figure 1. Point cloud data representation

下载: 全尺寸图片幻灯片

图 2 多源点云融合示例图

Figure 2. Example of multi-source point cloud fusion

下载: 全尺寸图片幻灯片

图 3 多帧点云融合示例图

Figure 3. Example of multi-frame point cloud fusion

下载: 全尺寸图片幻灯片

图 4 多视角点云融合示例图

Figure 4. Example of multi-view point cloud fusion

下载: 全尺寸图片幻灯片

图 5 多源点云融合时间线

Figure 5. Multi-source point cloud fusion timeline

下载: 全尺寸图片幻灯片

图 6 前融合3D模型开发和评估的流程图^[36]

Figure 6. Flowchart of pre-fusion 3D model development and evaluation^[36]

下载: 全尺寸图片幻灯片

图 7 PillarGrid Network^[43]

Figure 7. PillarGrid Network^[43]

下载: 全尺寸图片幻灯片

图 8 多专家学习框架^[51]

Figure 8. Multi-expert learning framework^[51]

下载: 全尺寸图片幻灯片

图 9 多帧点云融合时间线

Figure 9. Multi-frame point cloud fusion timeline

下载: 全尺寸图片幻灯片

图 10 基于LSTM的时序检测方法^[56]

Figure 10. LSTM-based time series detection method^[56]

下载: 全尺寸图片幻灯片

图 11 3D-MAN结构框图^[58]

Figure 11. 3D-MAN structure diagram^[58]

下载: 全尺寸图片幻灯片

图 12 利用点云序列进行离线三维目标检测的框架^[59]

Figure 12. Framework for offline 3D object detection using point cloud sequences^[59]

下载: 全尺寸图片幻灯片

图 13 多视角点云融合时间线

Figure 13. Multi-view point cloud fusion timeline

下载: 全尺寸图片幻灯片

图 14 改进的尺度PCA-ICP算法的实现过程^[69]

Figure 14. The implementation process of the improved scaled PCA-ICP algorithm^[69]

下载: 全尺寸图片幻灯片

图 15 多视图聚类框架^[71]

Figure 15. Multi-view clustering framework^[71]

下载: 全尺寸图片幻灯片

图 16 多视角激光点云拼接技术流程图^[77]

Figure 16. Multi-view laser point cloud stitching technology flow chart^[77]

下载: 全尺寸图片幻灯片

图 17 全向点云融合方法流程图^[78]

Figure 17. Flowchart of the omnidirectional point cloud fusion method^[78]

下载: 全尺寸图片幻灯片

表 1 铁路桥梁点云采集技术及融合算法

Table 1. Point cloud from capturing techniques and fusion algorithms of the railway bridge

点云数据	点的数量	精度(m)	平均覆盖率(%)	平均密度(标准差)(点/0.1 m³)
TLS: Leica P20	12,669,642	0.003	65.64	173 (102)
MLS: Navvis VLX2	18,401,315	0.006	65.30	259 (71)
SFM: DJI P4 + Pix4D	1,322,080	0.050	43.37	20.0 (8.0)
SOTA fusion	32,393,037	0.050	100	372 (146)
Weighted fusion	23,808,697	0.025	100	266 (14)

下载: 导出CSV

表 2 点云融合相关数据集

Table 2. Point cloud fusion related datasets

类型	数据集名称	主要传感器	优势	劣势
多源点云融合	KITTI^[23]	LiDAR、RGB摄像头、GPS	提供真实驾驶场景，广泛应用于自动驾驶领域	场景复杂性较低，较少覆盖复杂动态场景
	nuScenes^[24]	LiDAR、雷达、RGB摄像头、IMU	多种传感器数据同步，场景多样，标注丰富	数据量大，处理难度高
	Waymo Open Dataset^[28]	LiDAR、摄像头	更大规模的数据，覆盖复杂的城市驾驶场景	数据集体量庞大，计算资源需求较高
	A2D2^[29]	LiDAR、RGB摄像头、IMU、雷达	提供详细的传感器信息，丰富的驾驶场景	数据集较新，社区支持相对较少
	ApolloScape^[30]	LiDAR、RGB摄像头、GPS	大规模城市场景，支持3D点云与图像融合	数据质量不及KITTI等较为标准
多帧点云融合	Oxford RobotCar^[25]	LiDAR、相机、GPS、IMU	涵盖不同天气、光照条件下的长时间序列点云	数据复杂度高，长时间处理需要大量存储资源
	Argoverse^[31]	LiDAR、RGB摄像头、GPS	提供不同时间点的数据，支持多帧点云融合和动态场景检测	标注信息不如其他自动驾驶数据集丰富
	TUM RGB-D^[32]	RGB-D相机	提供室内动态场景的连续点云与图像	局限于室内环境，传感器类型单一
	Kaist Urban^[33]	LiDAR、相机、GPS、IMU	多帧时序数据丰富，场景涵盖日夜不同条件	主要集中于城市场景
多视角点云融合	斯坦福3D扫描模型库^[26]	用斯坦福大型雕塑扫描仪、Cyber ware 3030 MS扫描仪	包含9种不同目标的多视图扫描点云数据	无真实纹理或光照变化；数据规模较小，场景复杂度低
	UWA3M 数据集^[27]	RGB-D相机	提供物体实例级标注	场景多样性不足(主要为桌面物体)
	Augmented ICL-NUIM 数据集^[34]	合成RGB-D数据(模拟Kinect)	大型室内场景数据集，包含Living room 1, Living room 2, Office 1 和Office 2共4个场景序列	合成数据与真实传感器数据存在域差异；场景复杂度较低(多为室内简单布局)
	3DMatch^[35]	RGB-D相机	丰富的室内场景点云数据，适合多视角配准和3D重建	场景局限于室内，缺少室外复杂场景

下载: 导出CSV

参考文献(101)

[1]	ABBASI R, BASHIR A K, ALYAMANI H J, et al. Lidar point cloud compression, processing and learning for autonomous driving[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(1): 962–979. doi: 10.1109/TITS.2022.3167957.
[2]	QURESHI A H, ALALOUL W S, MURTIYOSO A, et al. Smart rebar progress monitoring using 3D point cloud model[J]. Expert Systems with Applications, 2024, 249: 123562. doi: 10.1016/j.eswa.2024.123562.
[3]	PETKOV P. Object detection and recognition with PointPillars in LiDAR point clouds-comparisions[R]. NSC-614-5849, 2024.
[4]	龚靖渝, 楼雨京, 柳奉奇, 等. 三维场景点云理解与重建技术[J]. 中国图象图形学报, 2023, 28(6): 1741–1766. doi: 10.11834/jig.230004. GONG Jingyu, LOU Yujing, LIU Fengqi, et al. Scene point cloud understanding and reconstruction technologies in 3D space[J]. Journal of Image and Graphics, 2023, 28(6): 1741–1766. doi: 10.11834/jig.230004.
[5]	ZHANG Bo, WANG Haosen, YOU Suilian, et al. A small-size 3D object detection network for analyzing the sparsity of raw LiDAR point cloud[J]. Journal of Russian Laser Research, 2023, 44(6): 646–655. doi: 10.1007/s10946-023-10173-3.
[6]	LI Shaorui, ZHU Zhenchang, DENG Weitang, et al. Estimation of aboveground biomass of different vegetation types in mangrove forests based on UAV remote sensing[J]. Sustainable Horizons, 2024, 11: 100100. doi: 10.1016/j.horiz.2024.100100.
[7]	余杭. 基于激光雷达的3D目标检测研究综述[J]. 汽车文摘, 2024(2): 18–27. doi: 10.19822/j.cnki.1671-6329.20230082. YU Hang. A review on LiDAR-based 3D target detection research[J]. Automotive Digest, 2024(2): 18–27. doi: 10.19822/j.cnki.1671-6329.20230082.
[8]	郭迟, 刘阳, 罗亚荣, 等. 图像语义信息在视觉SLAM中的应用研究进展[J]. 测绘学报, 2024, 53(6): 1057–1076. doi: 10.11947/j.AGCS.2024.20230259. GUO Chi, LIU Yang, LUO Yarong, et al. Research progress in the application of image semantic information in visual SLAM[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(6): 1057–1076. doi: 10.11947/j.AGCS.2024.20230259.
[9]	ZHANG L, VAN OOSTEROM P, and LIU H. Visualization of point cloud models in mobile augmented reality using continuous level of detail method[C]. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, London, UK, 2020: 167–170. doi: 10.5194/isprs-archives-XLIV-4-W1-2020-167-2020.
[10]	POLIYAPRAM V, WANG Weimin, and NAKAMURA R. A point-wise LiDAR and image multimodal fusion network (PMNet) for aerial point cloud 3D semantic segmentation[J]. Remote Sensing, 2019, 11(24): 2961. doi: 10.3390/rs11242961.
[11]	ZENG Tianjiao, ZHANG Wensi, ZHAN Xu, et al. A novel multimodal fusion framework based on point cloud registration for near-field 3D SAR perception[J]. Remote Sensing, 2024, 16(6): 952. doi: 10.3390/rs16060952.
[12]	CRISAN A, PEPE M, COSTANTINO D, et al. From 3D point cloud to an intelligent model set for cultural heritage conservation[J]. Heritage, 2024, 7(3): 1419–1437. doi: 10.3390/heritage7030068.
[13]	KIVILCIM C Ö and DURAN Z. A semi-automated point cloud processing methodology for 3D cultural heritage documentation[C]. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Prague, Czech Republic, 2016: 293–296. doi: 10.5194/isprs-archives-XLI-B5-293-2016.
[14]	WANG Yong, ZHOU Pengbo, GENG Guohua, et al. Enhancing point cloud registration with transformer: Cultural heritage protection of the Terracotta Warriors[J]. Heritage Science, 2024, 12(1): 314. doi: 10.1186/s40494-024-01425-9.
[15]	YANG Su, HOU Miaole, and LI Songnian. Three-dimensional point cloud semantic segmentation for cultural heritage: A comprehensive review[J]. Remote Sensing, 2023, 15(3): 548. doi: 10.3390/rs15030548.
[16]	李佳益, 马智亮, 陈礼杰, 等. 面向施工机器人定位的多模态数据融合方法研究综述[J]. 计算机工程与应用, 2024, 60(15): 11–23. doi: 10.3778/j.issn.1002-8331.2402-0008. LI Jiayi, MA Zhiliang, CHEN Lijie, et al. Comprehensive review of multimodal data fusion methods for construction robot localization[J]. Computer Engineering and Applications, 2024, 60(15): 11–23. doi: 10.3778/j.issn.1002-8331.2402-0008.
[17]	周燕, 李文俊, 党兆龙, 等. 深度学习的三维模型识别研究综述[J]. 计算机科学与探索, 2024, 18(4): 916–929. doi: 10.3778/j.issn.1673-9418.2309010. ZHOU Yan, LI Wenjun, DANG Zhaolong, et al. Survey of 3D model recognition based on deep learning[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(4): 916–929. doi: 10.3778/j.issn.1673-9418.2309010.
[18]	WANG Zhengren. 3D representation methods: A survey[J]. arXiv preprint arXiv, 2410.06475, 2024.
[19]	ZHOU Yin, SUN Pei, ZHANG Yu, et al. End-to-end multi-view fusion for 3D object detection in LiDAR point clouds[C]. The 3rd Annual Conference on Robot Learning, Osaka, Japan, 2019: 923–932.
[20]	陈慧娴, 吴一全, 张耀. 基于深度学习的三维点云分析方法研究进展[J]. 仪器仪表学报, 2023, 44(11): 130–158. doi: 10.19650/j.cnki.cjsi.J2311134. CHEN Huixian, WU Yiquan, and ZHANG Yao. Research progress of 3D point cloud analysis methods based on deep learning[J]. Chinese Journal of Scientific Instrument, 2023, 44(11): 130–158. doi: 10.19650/j.cnki.cjsi.J2311134.
[21]	LUO Haojun and WEN C Y. A low-cost relative positioning method for UAV/UGV coordinated heterogeneous system based on visual-lidar fusion[J]. Aerospace, 2023, 10(11): 924. doi: 10.3390/aerospace10110924.
[22]	LI Yangyan, BU Rui, SUN Mingchao, et al. PointCNN: Convolution on X-transformed points[C]. The 32nd International Conference on Neural Information Processing Systems, Montréal Canada, 2018: 828–838.
[23]	GEIGER A, LENZ P, STILLER C, et al. Vision meets robotics: The KITTI dataset[J]. The International Journal of Robotics Research, 2013, 32(11): 1231–1237. doi: 10.1177/0278364913491297.
[24]	CAESAR H, BANKITI V, LANG A H, et al. nuScenes: A multimodal dataset for autonomous driving[C]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, 2020: 11621–11631. DOI: 10.1109/CVPR42600.2020.01164.
[25]	MADDERN W, PASCOE G, LINEGAR C, et al. 1 year, 1000 km: The oxford robotcar dataset[J]. The International Journal of Robotics Research, 2017, 36(1): 3–15. doi: 10.1177/0278364916679498.
[26]	CURLESS B and LEVOY M. A volumetric method for building complex models from range images[C]. The 23rd Annual Conference on Computer Graphics and Interactive Techniques, New Orleans, USA, 1996: 303–312. doi: 10.1145/237170.237269.
[27]	MIAN A S, BENNAMOUN M, and OWENS R A. A novel representation and feature matching algorithm for automatic pairwise registration of range images[J]. International Journal of Computer Vision, 2006, 66(1): 19–40. doi: 10.1007/s11263-005-3221-0.
[28]	SUN Pei, KRETZSCHMAR H, DOTIWALLA X, et al. Scalability in perception for autonomous driving: Waymo open dataset[C]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, 2020: 2446–2454. doi: 10.1109/CVPR42600.2020.00252.
[29]	GEYER J, KASSAHUN Y, MAHMUDI M, et al. A2D2: Audi autonomous driving dataset[J]. arXiv preprint arXiv, 2004.06320, 2020.
[30]	HUANG Xinyu, CHENG Xinjing, GENG Qichuan, et al. The apolloscape dataset for autonomous driving[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, USA, 2018: 954–960. doi: 10.1109/CVPRW.2018.00141.
[31]	CHANG Mingfang, LAMBERT J, SANGKLOY P, et al. Argoverse: 3D tracking and forecasting with rich maps[C]. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019: 8748–8757. doi: 10.1109/CVPR.2019.00895.
[32]	STURM J, BURGARD W, and CREMERS D. Evaluating egomotion and structure-from-motion approaches using the TUM RGB-D benchmark[C]. The Workshop on Color-Depth Camera Fusion in Robotics at the IEEE/RJS International Conference on Intelligent Robot Systems, Vilamoura, Algarve, 2012: 6.
[33]	CHOI Y, KIM N, HWANG S, et al. KAIST multi-spectral day/night data set for autonomous and assisted driving[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 19(3): 934–948. doi: 10.1109/TITS.2018.2791533.
[34]	CHOI S, ZHOU Qianyi, and KOLTUN V. Robust reconstruction of indoor scenes[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 5556–5565. doi: 10.1109/CVPR.2015.7299195.
[35]	ZENG A, SONG S, NIEßNER M, et al. 3DMatch: Learning local geometric descriptors from RGB-D reconstructions[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 1802–1811. doi: 1 0.1109/CVPR.2017.29.
[36]	ABDELAZEEM M, ELAMIN A, AFIFI A, et al. Multi-sensor point cloud data fusion for precise 3D mapping[J]. The Egyptian Journal of Remote Sensing and Space Science, 2021, 24(3): 835–844. doi: 10.1016/j.ejrs.2021.06.002.
[37]	CÓRDOVA-ESPARZA D M, TERVEN J R, JIMÉNEZ-HERNÁNDEZ H, et al. A multiple camera calibration and point cloud fusion tool for Kinect V2[J]. Science of Computer Programming, 2017, 143: 1–8. doi: 10.1016/j.scico.2016.11.004.
[38]	PANAGIOTIDIS D, ABDOLLAHNEJAD A, and SLAVÍK M. 3D point cloud fusion from UAV and TLS to assess temperate managed forest structures[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 112: 102917. doi: 10.1016/j.jag.2022.102917.
[39]	YANG Weijun, LIU Yang, HE Huagui, et al. Airborne LiDAR and photogrammetric point cloud fusion for extraction of urban tree metrics according to street network segmentation[J]. IEEE Access, 2021, 9: 97834–97842. doi: 10.1109/ACCESS.2021.3094307.
[40]	PARVAZ S, TEFERLE F, and NURUNNABI A. Airborne cross-source point clouds fusion by slice-to-slice adjustment[C]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Athens, Greece, 2024: 161–168. doi: 10.5194/isprs-annals-X-4-W4-2024-161-2024.
[41]	CHENG Hongtai and HAN Jiayi. Toward precise dense 3D reconstruction of indoor hallway: A confidence-based panoramic LiDAR point cloud fusion approach[J]. Industrial Robot, 2025, 52(1): 116–125. doi: 10.1108/IR-03-2024-0132.
[42]	LI Shiming, GE Xuming, HU Han, et al. Laplacian fusion approach of multi-source point clouds for detail enhancement[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 171: 385–396. doi: 10.1016/j.isprsjprs.2020.11.021.
[43]	BAI Zhengwei, WU Guoyuan, BARTH M J, et al. PillarGrid: Deep learning-based cooperative perception for 3D object detection from onboard-roadside LiDAR[C]. 2022 IEEE 25th International Conference on Intelligent Transportation Systems, Macau, China, 2022: 1743–1749. doi: 10.1109/ITSC55140.2022.9921947.
[44]	ZHANG Pengcheng, HE Huagui, WANG Yun, et al. 3D urban buildings extraction based on airborne LiDAR and photogrammetric point cloud fusion according to U-Net deep learning model segmentation[J]. IEEE Access, 2022, 10: 20889–20897. doi: 10.1109/ACCESS.2022.3152744.
[45]	GUO Lijie, WU Yanjie, DENG Lei, et al. A feature-level point cloud fusion method for timber volume of forest stands estimation[J]. Remote Sensing, 2023, 15(12): 2995. doi: 10.3390/rs15122995.
[46]	QIAO Donghao and ZULKERNINE F. Adaptive feature fusion for cooperative perception using LiDAR point clouds[C]. 2023 IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, USA, 2023: 1186–1195. doi: 10.1109/WACV56688.2023.00124.
[47]	GRIFONI E, VANNINI E, LUNGHI I, et al. 3D multi-modal point clouds data fusion for metrological analysis and restoration assessment of a panel painting[J]. Journal of Cultural Heritage, 2024, 66: 356–366. doi: 10.1016/j.culher.2023.12.007.
[48]	CHEN Qi, TANG Sihai, YANG Qing, et al. Cooper: Cooperative perception for connected autonomous vehicles based on 3D point clouds[C]. 2019 IEEE 39th International Conference on Distributed Computing Systems, Dallas, USA, 2019: 514–524. doi: 10.1109/ICDCS.2019.00058.
[49]	HURL B, COHEN R, CZARNECKI K, et al. TruPercept: Trust modelling for autonomous vehicle cooperative perception from synthetic data[C]. 2020 IEEE Intelligent Vehicles Symposium, Las Vegas, USA, 2020: 341–347. doi: 10.1109/IV47402.2020.9304695.
[50]	LI Jie, ZHUANG Yiqi, PENG Qi, et al. Pose estimation of non-cooperative space targets based on cross-source point cloud fusion[J]. Remote Sensing, 2021, 13(21): 4239. doi: 10.3390/rs13214239.
[51]	TANG Zhiri, HU Ruihan, CHEN Yanhua, et al. Multi-expert learning for fusion of pedestrian detection bounding box[J]. Knowledge-Based Systems, 2022, 241: 108254. doi: 10.1016/j.knosys.2022.108254.
[52]	YU Haibao, LUO Yizhen, SHU Mao, et al. DAIR-V2X: A large-scale dataset for vehicle-infrastructure cooperative 3D object detection[C]. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA, 2022: 21361–21370. doi: 10.1109/CVPR52688.2022.02067.
[53]	RIZALDY A, AFIFI A J, GHAMISI P, et al. Dimensional dilemma: Navigating the fusion of hyperspectral and LiDAR point cloud data for optimal precision-2D vs. 3D[C]. 2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece, 2024: 7729–7733. doi: 10.1109/IGARSS53475.2024.10641140.
[54]	LUO Wenjie, YANG Bin, and URTASUN R. Fast and furious: Real time end-to-end 3D detection, tracking and motion forecasting with a single convolutional net[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 3569–3577. doi: 10.1109/CVPR.2018.00376.
[55]	LI Jing, LI Rui, WANG Junzheng, et al. Obstacle information detection method based on multiframe three-dimensional lidar point cloud fusion[J]. Optical Engineering, 2019, 58(11): 116102. doi: 10.1117/1.OE.58.11.116102.
[56]	HUANG Rui, ZHANG Wanyue, KUNDU A, et al. An LSTM approach to temporal 3D object detection in LiDAR point clouds[C]. The 16th European Conference on Computer Vision, Glasgow, UK, 2020: 266–282. doi: 10.1007/978-3-030-58523-5_16.
[57]	YIN Junbo, SHEN Jianbing, GUAN Chenye, et al. LiDAR-based online 3D video object detection with graph-based message passing and spatiotemporal transformer attention[C]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, 2020: 11495–11504. doi: 10.1109/CVPR42600.2020.01151.
[58]	YANG Zetong, ZHOU Yin, CHEN Zhifeng, et al. 3D-MAN: 3D multi-frame attention network for object detection[C]. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA, 2021: 1863–1872. doi: 10.1109/CVPR46437.2021.00190.
[59]	QI C R, ZHOU Yin, NAJIBI M, et al. Offboard 3D object detection from point cloud sequences[C]. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA, 2021: 6134–6144. doi: 10.1109/CVPR46437.2021.00607.
[60]	SUN Pei, WANG Weiyue, CHAI Yuning, et al. RSN: Range sparse net for efficient, accurate LiDAR 3D object detection[C]. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA, 2021: 5725–5734. doi: 10.1109/CVPR46437.2021.00567.
[61]	YIN Tianwei, ZHOU Xingyi, and KRÄHENBÜHL P. Center-based 3D object detection and tracking[C]. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA, 2021: 11784–11793. doi: 10.1109/CVPR46437.2021.01161.
[62]	LUO Chenxu, YANG Xiaodong, and YUILLE A. Exploring simple 3D multi-object tracking for autonomous driving[C]. 2021 IEEE/CVF International Conference on Computer Vision, Montreal, Canada, 2021: 10488–10497. doi: 10.1109/ICCV48922.2021.01032.
[63]	毛冬海, 李守军, 王锋, 等. LiDAR测量点云融合影像的分块滤波方法[J]. 测绘通报, 2021(10): 67–72, 131. doi: 10.13474/j.cnki.11-2246.2021.307. MAO Donghai, LI Shoujun, WANG Feng, et al. Block filtering method for LiDAR point cloud fusion image[J]. Bulletin of Surveying and Mapping, 2021(10): 67–72, 131. doi: 10.13474/j.cnki.11-2246.2021.307.
[64]	CHEN Xuesong, SHI Shaoshuai, ZHU Benjin, et al. MPPNet: Multi-frame feature intertwining with proxy points for 3D temporal object detection[C]. The 17th European Conference on Computer Vision, Tel Aviv, Israel, 2022: 680–697. doi: 10.1007/978-3-031-20074-8_39.
[65]	HU Yihan, DING Zhuangzhuang, GE Runzhou, et al. AFDetV2: Rethinking the necessity of the second stage for object detection from point clouds[C]. The 36th AAAI Conference on Artificial Intelligence, 2022: 969–979. doi: 10.1609/aaai.v36i1.19980.
[66]	HE Chenhang, LI Ruihuang, ZHANG Yabin, et al. MSF: Motion-guided sequential fusion for efficient 3D object detection from point cloud sequences[C]. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, Canada, 2023: 5196–5205. doi: 10.1109/CVPR52729.2023.00503.
[67]	SHI Lingfeng, LV Yunfeng, YIN Wei, et al. Autonomous multiframe point cloud fusion method for mmWave radar[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 4505708. doi: 10.1109/TIM.2023.3302936.
[68]	YANG Yanding, JIANG Kun, YANG Diange, et al. Temporal point cloud fusion with scene flow for robust 3D object tracking[J]. IEEE Signal Processing Letters, 2022, 29: 1579–1583. doi: 10.1109/LSP.2022.3185948.
[69]	CHEN Hui, FENG Yan, YANG Jian, et al. 3D reconstruction approach for outdoor scene based on multiple point cloud fusion[J]. Journal of the Indian Society of Remote Sensing, 2019, 47(10): 1761–1772. doi: 10.1007/s12524-019-01029-y.
[70]	CHENG Yuqi, LI Wenlong, JIANG Cheng, et al. MVGR: Mean-variance minimization global registration method for multiview point cloud in robot inspection[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 8504915. doi: 10.1109/TIM.2024.3413191.
[71]	LIU Junjie, LIU Junlong, YAN Shaotian, et al. MPC: Multi-view probabilistic clustering[C]. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA, 2022: 9509–9518. doi: 10.1109/CVPR52688.2022.00929.
[72]	KLOEKER L, KOTULLA C, and ECKSTEIN L. Real-time point cloud fusion of multi-LiDAR infrastructure sensor setups with unknown spatial location and orientation[C]. 2020 IEEE 23rd International Conference on Intelligent Transportation Systems, Rhodes, Greece, 2020: 1–8. doi: 10.1109/ITSC45102.2020.9294312.
[73]	YU Xumin, TANG Lulu, RAO Yongming, et al. Point-BERT: Pre-training 3D point cloud transformers with masked point modeling[C]. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA, 2022: 19313–19322. doi: 10.1109/CVPR52688.2022.01871.
[74]	LI Yao, ZHOU Yong, ZHAO Jiaqi, et al. FA-MSVNet: Multi-scale and multi-view feature aggregation methods for stereo 3D reconstruction[J]. Multimedia Tools and Applications, 2024: 1–23. doi: 10.1007/s11042-024-20431-4.
[75]	CHEN Zhimin, LI Yingwei, JING Longlong, et al. Point cloud self-supervised learning via 3D to multi-view masked autoencoder[J]. arXiv preprint arXiv, 2311.10887, 2023.
[76]	LING Xiao and QIN Rongjun. A graph-matching approach for cross-view registration of over-view and street-view based point clouds[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 185: 2–15. doi: 10.1016/j.isprsjprs.2021.12.013.
[77]	深圳市博大建设集团有限公司. 一种多视角三维激光点云拼接方法及系统[P]. 中国, 202411659468.1, 2024. Shenzhen Boda Construction Group Co., Ltd. Multi-view three-dimensional laser point cloud splicing method and system[P]. CN, 202411659468.1, 2024.
[78]	北京鹏太光耀科技有限公司. 一种基于多目结构光的全向点云融合方法[P]. 中国, 202411346535.4, 2025. Beijing Pengtai Guangyao Technology Co., Ltd. Omnidirectional point cloud fusion method based on multi-view structured light[P]. CN, 202411346535.4, 2025.
[79]	KHAN K N, KHALID A, TURKAR Y, et al. VRF: Vehicle road-side point cloud fusion[C]. The 22nd Annual International Conference on Mobile Systems, Applications and Services, Tokyo, Japan, 2024: 547–560. doi: 10.1145/3643832.3661874.
[80]	BREYER M, OTT L, SIEGWART R, et al. Closed-loop next-best-view planning for target-driven grasping[C]. 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, Kyoto, Japan, 2022: 1411–1416. doi: 10.1109/IROS47612.2022.9981472.
[81]	JIANG Changjian, GAO Ruilan, SHAO Kele, et al. LI-GS: Gaussian splatting with LiDAR incorporated for accurate large-scale reconstruction[J]. IEEE Robotics and Automation Letters, 2025, 10(2): 1864–1871. doi: 10.1109/LRA.2024.3522846.
[82]	YANG Shuo, LU Huimin, and LI Jianru. Multifeature fusion-based object detection for intelligent transportation systems[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(1): 1126–1133. doi: 10.1109/TITS.2022.3155488.
[83]	MA Nan, XIAO Chuansheng, WANG Mohan, et al. A review of point cloud and image cross-modal fusion for self-driving[C]. 2022 18th International Conference on Computational Intelligence and Security, Chengdu, China, 2022: 456–460. doi: 10.1109/CIS58238.2022.00103.
[84]	LIU Zhijian, TANG Haotian, AMINI A, et al. BEVFusion: Multi-task multi-sensor fusion with unified bird's-eye view representation[C]. 2023 IEEE International Conference on Robotics and Automation, London, UK, 2023: 2774–2781. doi: 10.1109/ICRA48891.2023.10160968.
[85]	KUMAR G A, LEE J H, HWANG J, et al. LiDAR and camera fusion approach for object distance estimation in self-driving vehicles[J]. Symmetry, 2020, 12(2): 324. doi: 10.3390/sym12020324.
[86]	HUANG Keli, SHI Botian, LI Xiang, et al. Multi-modal sensor fusion for auto driving perception: A survey[J]. arXiv preprint arXiv, 2202.02703, 2022.
[87]	CAI Yiyi, OU Yang, and QIN Tuanfa. Improving SLAM techniques with integrated multi-sensor fusion for 3D reconstruction[J]. Sensors, 2024, 24(7): 2033. doi: 10.3390/s24072033.
[88]	RODRIGUEZ-GARCIA B, RAMÍREZ-SANZ J M, MIGUEL-ALONSO I, et al. Enhancing learning of 3D model unwrapping through virtual reality serious game: Design and usability validation[J]. Electronics, 2024, 13(10): 1972. doi: 10.3390/electronics13101972.
[89]	KAVALIAUSKAS P, FERNANDEZ J B, MCGUINNESS K, et al. Automation of construction progress monitoring by integrating 3D point cloud data with an IFC-based BIM model[J]. Buildings, 2022, 12(10): 1754. doi: 10.3390/buildings12101754.
[90]	XU Yusheng and STILLA U. Toward building and civil infrastructure reconstruction from point clouds: A review on data and key techniques[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 2857–2885. doi: 10.1109/JSTARS.2021.3060568.
[91]	JHONG S Y, CHEN Y Y, HSIA C H, et al. Density-aware and semantic-guided fusion for 3-D object detection using LiDAR-camera sensors[J]. IEEE Sensors Journal, 2023, 23(18): 22051–22063. doi: 10.1109/JSEN.2023.3302314.
[92]	LUO Zhipeng, ZHOU Changqing, PAN Liang, et al. Exploring point-BEV fusion for 3D point cloud object tracking with transformer[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(9): 5921–5935. doi: 10.1109/TPAMI.2024.3373693.
[93]	LIU Jianan, ZHAO Qiuchi, XIONG Weiyi, et al. SMURF: Spatial multi-representation fusion for 3D object detection with 4D imaging radar[J]. IEEE Transactions on Intelligent Vehicles, 2024, 9(1): 799–812. doi: 10.1109/TIV.2023.3322729.
[94]	HAO Ruidong, WEI Zhongwei, HE Xu, et al. Robust point cloud registration network for complex conditions[J]. Sensors, 2023, 23(24): 9837. doi: 10.3390/s23249837.
[95]	BAYRAK O C, MA Zhenyu, MARIAROSARIA FARELLA E, et al. Operationalize large-scale point cloud classification: Potentials and challenges[C]. EGU General Assembly Conference Abstracts 2024, Vienna, Austria, 2024: 10034. doi: 10.5194/egusphere-egu24-10034.
[96]	SHAN Shuo, LI Chenxi, WANG Yiye, et al. A deep learning model for multi-modal spatio-temporal irradiance forecast[J]. Expert Systems with Applications, 2024, 244: 122925. doi: 10.1016/j.eswa.2023.122925.
[97]	QIAN Jiaming, FENG Shijie, TAO Tianyang, et al. Real-time 3D point cloud registration[C]. SPIE 11205, Seventh International Conference on Optical and Photonic Engineering, Phuket, Thailand, 2019: 495–500. doi: 10.1117/12.2547865.
[98]	SHI Fengyuan, ZHENG Xunjiang, JIANG Lihui, et al. Fast point cloud registration algorithm using parallel computing strategy[J]. Journal of Physics: Conference Series, 2022, 2235(1): 012104. doi: 10.1088/1742-6596/2235/1/012104.
[99]	LUO Yukui. Securing FPGA as a shared cloud-computing resource: Threats and mitigations[D]. [Ph.D. dissertation], Northeastern University, 2023.
[100]	WANG Laichao, LU Weiding, TIAN Yuan, et al. 6D object pose estimation with attention aware Bi-gated fusion[C]. The 30th International Conference on Neural Information Processing, Changsha, China, 2024: 573–585. doi: 10.1007/978-981-99-8082-6_44.
[101]	HONG Jiaxin, ZHANG Hongbo, LIU Jinghua, et al. A transformer-based multi-modal fusion network for 6D pose estimation[J]. Information Fusion, 2024, 105: 102227. doi: 10.1016/j.inffus.2024.102227.