{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T21:24:23Z","timestamp":1775683463386,"version":"3.50.1"},"reference-count":113,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T00:00:00Z","timestamp":1718323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T00:00:00Z","timestamp":1718323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Fund Project of Central Government Guided Local Science and Technology Development","award":["226Z0302G"],"award-info":[{"award-number":["226Z0302G"]}]},{"name":"Fund Project of Central Government Guided Local Science and Technology Development","award":["226Z0302G"],"award-info":[{"award-number":["226Z0302G"]}]},{"name":"Special Project of Langfang Key Research and Development","award":["2023011005B"],"award-info":[{"award-number":["2023011005B"]}]},{"name":"Special Project of Langfang Key Research and Development","award":["2023011005B"],"award-info":[{"award-number":["2023011005B"]}]},{"name":"Special Project of Langfang Key Research and Development","award":["2023011005B"],"award-info":[{"award-number":["2023011005B"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s00371-024-03480-6","type":"journal-article","created":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T19:01:28Z","timestamp":1718391688000},"page":"1757-1775","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["A review of 3D object detection based on autonomous driving"],"prefix":"10.1007","volume":"41","author":[{"given":"Huijuan","family":"Wang","sequence":"first","affiliation":[]},{"given":"Xinyue","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Quanbo","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Peng","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,6,14]]},"reference":[{"issue":"2","key":"3480_CR1","doi-asserted-by":"publisher","first-page":"1152","DOI":"10.1109\/JSEN.2020.3020626","volume":"21","author":"Y Wu","year":"2020","unstructured":"Wu, Y., Wang, Y., Zhang, S., et al.: Deep 3D object detection networks using LiDAR data: a review. IEEE Sens. J. 21(2), 1152\u20131171 (2020)","journal-title":"IEEE Sens. J."},{"key":"3480_CR2","doi-asserted-by":"crossref","unstructured":"Shreyas E, Sheth MH: 3D object detection and tracking methods using deep learning for computer vision applications. In: Proceedings of the 2021 International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT). IEEE. (2021)","DOI":"10.1109\/RTEICT52294.2021.9573964"},{"key":"3480_CR3","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1016\/j.neucom.2021.11.048","volume":"471","author":"J Mao","year":"2022","unstructured":"Mao, J., Shi, S., Wang, X., et al.: 3d object detection for autonomous driving: a review and new outlooks. Neurocomputing 471, 219\u2013229 (2022)","journal-title":"Neurocomputing"},{"key":"3480_CR4","doi-asserted-by":"crossref","unstructured":"Chen X, Ma H, Wan J, et al.: Multi-view 3d object detection network for autonomous driving. In: proceedings of the Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.691"},{"key":"3480_CR5","doi-asserted-by":"crossref","unstructured":"Ku J, Mozifian M, Lee J, et al. Joint 3d proposal generation and object detection from view aggregation. In: Proceedings of the 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE (2018)","DOI":"10.1109\/IROS.2018.8594049"},{"key":"3480_CR6","doi-asserted-by":"crossref","unstructured":"Shi S, Wang X, Li HP.: 3d object proposal generation and detection from point cloud. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"3480_CR7","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R.: Are we ready for autonomous driving? The kitti vision benchmark suite. In: Proceedings of the 2012 IEEE conference on computer vision and pattern recognition. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"3480_CR8","doi-asserted-by":"crossref","unstructured":"Caesar H, Bankiti V, Lang AH, et al.: Nuscenes: A multimodal dataset for autonomous driving. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"3480_CR9","doi-asserted-by":"crossref","unstructured":"Sun P, Kretzschmar H, Dotiwalla X, et al.: Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"issue":"10","key":"3480_CR10","doi-asserted-by":"publisher","first-page":"2702","DOI":"10.1109\/TPAMI.2019.2926463","volume":"42","author":"X Huang","year":"2019","unstructured":"Huang, X., Wang, P., Cheng, X., et al.: The apolloscape open dataset for autonomous driving and its application. IEEE Trans. Pattern Anal. Mach. Intell.Intell. 42(10), 2702\u20132719 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.Intell."},{"key":"3480_CR11","doi-asserted-by":"crossref","unstructured":"Dai A, Chang A X, Savva M, et al.: Scannet: Richly-annotated 3d reconstructions of indoor scenes. In: Proceedings of the Proceedings of the IEEE conference on computer vision and pattern recognition (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"3480_CR12","doi-asserted-by":"crossref","unstructured":"Song S, Lichtenberg S P, Xiao J.: Sun rgb-d: A rgb-d scene understanding benchmark suite. In: Proceedings of the Proceedings of the IEEE conference on computer vision and pattern recognition (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"3480_CR13","unstructured":"Wu Z, Song S, Khosla A, et al.: 3d shapenets: A deep representation for volumetric shapes. In: Proceedings of the Proceedings of the IEEE conference on computer vision and pattern recognition (2015)"},{"key":"3480_CR14","unstructured":"Qi CR, Su H, Mo K, et al.: Pointnet: Deep learning on point sets for 3d classification and segmentation. In: Proceedings of the Proceedings of the IEEE conference on computer vision and pattern recognition (2017)"},{"key":"3480_CR15","unstructured":"Qi C R, Yi L, Su H, et al.: Pointnet++: Deep hierarchical feature learning on point sets in a metric space. In: Advances in neural information processing systems (2017)"},{"key":"3480_CR16","doi-asserted-by":"crossref","unstructured":"Qi CR, Litany O, He K, et al.: Deep hough voting for 3d object detection in point clouds. In: Proceedings of the proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"3480_CR17","doi-asserted-by":"crossref","unstructured":"Shi S, Wang X, Li H.: Pointrcnn: 3d object proposal generation and detection from point cloud. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"3480_CR18","doi-asserted-by":"crossref","unstructured":"Yang Z, Sun Y, Liu S, et al.: Std: Sparse-to-dense 3d object detector for point cloud; proceedings of the Proceedings of the IEEE\/CVF international conference on computer vision (2019)","DOI":"10.1109\/ICCV.2019.00204"},{"key":"3480_CR19","doi-asserted-by":"crossref","unstructured":"Yang Z, Sun Y, Liu S, et al.: 3dssd: Point-based 3d single stage object detector. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"3480_CR20","doi-asserted-by":"crossref","unstructured":"Zheng W, Tang W, Jiang L, et al.: SE-SSD: Self-ensembling single-stage object detector from point cloud. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"3480_CR21","doi-asserted-by":"crossref","unstructured":"Yin T, Zhou X, Krahenbuhl P.: Center-based 3d object detection and tracking. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"3480_CR22","doi-asserted-by":"crossref","unstructured":"Pan X, Xia Z, Song S, et al.: 3d object detection with pointformer. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"3480_CR23","doi-asserted-by":"crossref","unstructured":"Chen C, Chen Z, Zhang J et al.: Sasa: Semantics-augmented set abstraction for point-based 3d object detection. In: proceedings of the Proceedings of the AAAI Conference on Artificial Intelligence (2022)","DOI":"10.1609\/aaai.v36i1.19897"},{"key":"3480_CR24","doi-asserted-by":"crossref","unstructured":"Zhang B, Yuan J, Shi B, et al.: Uni3d: A unified baseline for multi-dataset 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00893"},{"key":"3480_CR25","unstructured":"Zarzar J, Giancola S, Ghanem BJAPA.: PointRGCN: Graph convolution networks for 3D vehicles detection refinement (2019)"},{"key":"3480_CR26","doi-asserted-by":"crossref","unstructured":"Shi W, Rajkumar R.: Point-gnn: Graph neural network for 3d object detection in a point cloud. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"3480_CR27","doi-asserted-by":"crossref","unstructured":"Chen J, Lei B, Song Q, et al.: A hierarchical graph network for 3d object detection on point clouds. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00047"},{"key":"3480_CR28","doi-asserted-by":"crossref","unstructured":"Zhao N, Chua T-S, Lee G H.: Sess: Self-ensembling semi-supervised 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01109"},{"key":"3480_CR29","doi-asserted-by":"crossref","unstructured":"Wang H, Cong Y, Litany O, et al.: 3dioumatch: Leveraging iou prediction for semi-supervised 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01438"},{"key":"3480_CR30","doi-asserted-by":"crossref","unstructured":"Yang J, Shi S, Wang Z, et al.: St3d: Self-training for unsupervised domain adaptation on 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01023"},{"issue":"5","key":"3480_CR31","first-page":"6354","volume":"45","author":"J Yang","year":"2022","unstructured":"Yang, J., Shi, S., Wang, Z., et al.: ST3D++: Denoised Self-Training for Unsupervised Domain Adaptation on 3D Object Detection. IEEE Trans. Pattern Anal. Mach. Intell.Intell. 45(5), 6354\u20136371 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.Intell."},{"key":"3480_CR32","doi-asserted-by":"crossref","unstructured":"Xu X, Wang Y, Zheng Y, et al.: Back to reality: Weakly-supervised 3d object detection with shape-guided label enhancement. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00825"},{"key":"3480_CR33","doi-asserted-by":"crossref","unstructured":"Engelcke M, Rao D, Wang D Z, et al.: Vote3deep: Fast object detection in 3d point clouds using efficient convolutional neural networks. In: Proceedings of the 2017 IEEE International Conference on Robotics and Automation (ICRA) IEEE (2017).","DOI":"10.1109\/ICRA.2017.7989161"},{"key":"3480_CR34","doi-asserted-by":"crossref","unstructured":"Zhou Y, Tuzel O.: Voxelnet: End-to-end learning for point cloud based 3d object detection. In: Proceedings of the Proceedings of the IEEE conference on computer vision and pattern recognition (2018)","DOI":"10.1109\/CVPR.2018.00472"},{"issue":"10","key":"3480_CR35","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan, Y., Mao, Y., Li, B.J.S.: Second: Sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018)","journal-title":"Sensors"},{"key":"3480_CR36","doi-asserted-by":"crossref","unstructured":"Lang A H, Vora S, Caesar H, et al.: Pointpillars: Fast encoders for object detection from point clouds. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"issue":"3","key":"3480_CR37","doi-asserted-by":"publisher","first-page":"704","DOI":"10.3390\/s20030704","volume":"20","author":"H Kuang","year":"2020","unstructured":"Kuang, H., Wang, B., An, J., et al.: Voxel-FPN: Multi-scale voxel feature aggregation for 3D object detection from LIDAR point clouds. Sensors 20(3), 704 (2020)","journal-title":"Sensors"},{"key":"3480_CR38","doi-asserted-by":"crossref","unstructured":"Ye M, Xu S, Cao T.: Hvnet: Hybrid voxel network for lidar based 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00170"},{"key":"3480_CR39","doi-asserted-by":"crossref","unstructured":"Deng J, Shi S, Li P, et al.: Voxel r-cnn: Towards high performance voxel-based 3d object detection. In: Proceedings of the Proceedings of the AAAI Conference on Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"3480_CR40","doi-asserted-by":"crossref","unstructured":"He C, Li R, Li S, et al.: Voxel set transformer: A set-to-set approach to 3d object detection from point clouds. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00823"},{"key":"3480_CR41","unstructured":"Li B, Zhang T, Xia TJAP A.: Vehicle detection from 3d lidar using fully convolutional network. arXiv (2016)"},{"key":"3480_CR42","doi-asserted-by":"crossref","unstructured":"Yang B, Luo W, Urtasun R.: Pixor: Real-time 3d object detection from point clouds. In: Proceedings of the Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00798"},{"key":"3480_CR43","unstructured":"Yang B, Liang M, Urtasun R.: Hdnet: Exploiting hd maps for 3d object detection. In: Proceedings of the Conference on Robot Learning PMLR (2018)"},{"key":"3480_CR44","doi-asserted-by":"crossref","unstructured":"Beltr\u00e1n J, Guindel C, Moreno F M, et al.: Birdnet: a 3d object detection framework from lidar information. In: Proceedings of the 2018 21st International Conference on Intelligent Transportation Systems (ITSC) IEEE (2018)","DOI":"10.1109\/ITSC.2018.8569311"},{"key":"3480_CR45","doi-asserted-by":"crossref","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster r-cnn: Towards real-time object detection with region proposal networks. In: IEEE transactions on pattern analysis and machine intelligence (2016)","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"3480_CR46","doi-asserted-by":"crossref","unstructured":"Meyer G P, Laddha A, Kee E, et al.: Lasernet: An efficient probabilistic 3d object detector for autonomous driving. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2019)","DOI":"10.1109\/CVPR.2019.01296"},{"key":"3480_CR47","unstructured":"Bewley A, Sun P, Mensink T, et al.: Range conditioned dilated convolutions for scale invariant 3d object detection (2020). arxiv:2005.09927"},{"key":"3480_CR48","doi-asserted-by":"crossref","unstructured":"Fan L, Xiong X, Wang F, et al.: Rangedet: In defense of range view for lidar-based 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF international conference on computer vision (2021)","DOI":"10.1109\/ICCV48922.2021.00291"},{"key":"3480_CR49","doi-asserted-by":"crossref","unstructured":"Sun P, Wang W, Chai Y, et al.: Rsn: Range sparse net for efficient, accurate lidar 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00567"},{"key":"3480_CR50","doi-asserted-by":"crossref","unstructured":"Duan K, Bai S, Xie L, et al.: Centernet: Keypoint triplets for object detection. In: Proceedings of the Proceedings of the IEEE\/CVF international conference on computer vision (2019)","DOI":"10.1109\/ICCV.2019.00667"},{"key":"3480_CR51","doi-asserted-by":"crossref","unstructured":"Deng S, Liang Z, Sun L, et al.: Vista: Boosting 3d object detection via dual cross-view spatial attention. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00826"},{"key":"3480_CR52","unstructured":"Tian, Z., Chu, X., Wang, X., et al.: Fully convolutional one-stage 3d object detection on lidar range images. In: Advances in Neural Information Processing Systems (2022)"},{"key":"3480_CR53","doi-asserted-by":"crossref","unstructured":"Shi S, Guo C, Jiang L, et al.: Pv-rcnn: Point-voxel feature set abstraction for 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"3480_CR54","doi-asserted-by":"crossref","unstructured":"Chen Y, Liu S, Shen X, et al.: Fast point r-cnn. In: Proceedings of the Proceedings of the IEEE\/CVF international conference on computer vision (2019)","DOI":"10.1109\/ICCV.2019.00987"},{"key":"3480_CR55","doi-asserted-by":"crossref","unstructured":"He C, Zeng H, Huang J, et al.: Structure aware single-stage 3d object detection from point cloud. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"3480_CR56","doi-asserted-by":"crossref","unstructured":"Noh J, Lee S, Ham B.: Hvpr: Hybrid voxel-point representation for single-stage 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01437"},{"key":"3480_CR57","doi-asserted-by":"crossref","unstructured":"Miao Z, Chen J, Pan H, et al.: Pvgnet: A bottom-up one-stage 3d object detector with integrated multi-level features. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00329"},{"key":"3480_CR58","unstructured":"Zhou Y, Sun P, Zhang Y, et al.: End-to-end multi-view fusion for 3d object detection in lidar point clouds. In: Proceedings of the Conference on Robot Learning, PMLR, (2020)"},{"key":"3480_CR59","unstructured":"Wang Y, Fathi A, Kundu A, et al.: Pillar-based object detection for autonomous driving; proceedings of the Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXII 16. Springer (2020)"},{"key":"3480_CR60","doi-asserted-by":"crossref","unstructured":"Fazlali H, Xu Y, Ren Y, et al.: A versatile multi-view framework for lidar-based 3d object detection with guidance from panoptic segmentation. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01668"},{"key":"3480_CR61","doi-asserted-by":"crossref","unstructured":"Chen X, Kundu K, Zhang Z, et al.: Monocular 3d object detection for autonomous driving. In: Proceedings of the Proceedings of the IEEE conference on computer vision and pattern recognition (2016)","DOI":"10.1109\/CVPR.2016.236"},{"key":"3480_CR62","doi-asserted-by":"crossref","unstructured":"Mousavian A, Anguelov D, Flynn J, et al.: 3d bounding box estimation using deep learning and geometry. In: Proceedings of the Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.597"},{"key":"3480_CR63","doi-asserted-by":"crossref","unstructured":"Xu B, Chen Z.: Multi-level fusion based 3d object detection from monocular images. In: Proceedings of the Proceedings of the IEEE conference on computer vision and pattern recognition (2018)","DOI":"10.1109\/CVPR.2018.00249"},{"key":"3480_CR64","doi-asserted-by":"crossref","unstructured":"Godard C, Mac Aodha O, Brostow G J.: Unsupervised monocular depth estimation with left-right consistency. In: Proceedings of the Proceedings of the IEEE conference on computer vision and pattern recognition (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"3480_CR65","doi-asserted-by":"crossref","unstructured":"Li B, Ouyang W, Sheng L, et al.: Gs3d: An efficient 3d object detection framework for autonomous driving. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (2019)","DOI":"10.1109\/CVPR.2019.00111"},{"key":"3480_CR66","doi-asserted-by":"crossref","unstructured":"Ku J, Pon A D, Waslander S L.: Monocular 3d object detection leveraging accurate proposals and shape reconstruction. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2019)","DOI":"10.1109\/CVPR.2019.01214"},{"key":"3480_CR67","doi-asserted-by":"crossref","unstructured":"Liu Z, Wu Z, T\u00f3th R.: Smoke: Single-stage monocular 3d object detection via keypoint estimation. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2020)","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"3480_CR68","doi-asserted-by":"crossref","unstructured":"Wang T, Zhu X, Pang J, et al.: Fcos3d: Fully convolutional one-stage monocular 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"3480_CR69","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, et al.: FCOS: Fully Convolutional One-Stage Object Detection. In: Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), F 27 Oct.-2 Nov. 2019, (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"3480_CR70","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, et al.: Deep residual learning for image recognition. In: Proceedings of the Proceedings of the IEEE conference on computer vision and pattern recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3480_CR71","doi-asserted-by":"crossref","unstructured":"Reading C, Harakeh A, Chae J, et al.: Categorical depth distribution network for monocular 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"3480_CR72","doi-asserted-by":"crossref","unstructured":"Chen H, Huang Y, Tian W, et al.: Monorun: Monocular 3d object detection by reconstruction and uncertainty propagation. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01024"},{"key":"3480_CR73","doi-asserted-by":"crossref","unstructured":"Luo S, Dai H, Shao L, et al.: M3dssd: Monocular 3d single stage object detector. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00608"},{"key":"3480_CR74","doi-asserted-by":"crossref","unstructured":"Park D, Ambrus R, Guizilini V, et al.: Is pseudo-lidar needed for monocular 3d object detection?. In: Proceedings of the Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"3480_CR75","doi-asserted-by":"crossref","unstructured":"Huang K-C, Wu T-H, Su H-T, et al.: Monodtr: Monocular 3d object detection with depth-aware transformer. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"3480_CR76","doi-asserted-by":"crossref","unstructured":"Lian Q, Li P, Chen X.: Monojsg: Joint semantic and geometric cost volume for monocular 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00114"},{"issue":"5","key":"3480_CR77","doi-asserted-by":"publisher","first-page":"1259","DOI":"10.1109\/TPAMI.2017.2706685","volume":"40","author":"X Chen","year":"2017","unstructured":"Chen, X., Kundu, K., Zhu, Y., et al.: 3d object proposals using stereo imagery for accurate object class detection. IEEE Trans. Pattern Anal. Mach. Intell.Intell. 40(5), 1259\u20131272 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.Intell."},{"key":"3480_CR78","doi-asserted-by":"crossref","unstructured":"Tsochantaridis I, Hofmann T, Joachims T, et al.: Support vector learning for interdependent and structured output spaces (ICML 04), 10(1015330.1015341) (2004)","DOI":"10.1145\/1015330.1015341"},{"key":"3480_CR79","doi-asserted-by":"crossref","unstructured":"Qin Z, Wang J, Lu Y.: Triangulation learning network: from monocular to stereo 3d object detection. In: proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00780"},{"key":"3480_CR80","doi-asserted-by":"crossref","unstructured":"Li P, Chen X, Shen S.: Stereo r-cnn based 3d object detection for autonomous driving. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00783"},{"key":"3480_CR81","doi-asserted-by":"crossref","unstructured":"Peng W, Pan H, Liu H, et al.: Ida-3d: Instance-depth-aware 3d object detection from stereo vision for autonomous driving. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01303"},{"key":"3480_CR82","doi-asserted-by":"crossref","unstructured":"Sun J, Chen L, Xie Y, et al.: Disp r-cnn: Stereo 3d object detection via shape prior guided instance disparity estimation. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01056"},{"key":"3480_CR83","doi-asserted-by":"crossref","unstructured":"Xu Z, Zhang W, Ye X, et al.: Zoomnet: Part-aware adaptive zooming neural network for 3d object detection. In: Proceedings of the Proceedings of the AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i07.6945"},{"key":"3480_CR84","doi-asserted-by":"crossref","unstructured":"Chen Y, Liu S, Shen X, et al.: Dsgn: Deep stereo geometry network for 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01255"},{"key":"3480_CR85","doi-asserted-by":"crossref","unstructured":"Liu Y, Wang L, Liu M.: Yolostereo3d: A step back to 2d for efficient stereo 3d detection. In: Proceedings of the 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9561423"},{"key":"3480_CR86","doi-asserted-by":"crossref","unstructured":"Chen, Y., Huang, S., Liu, S., et al.: DSGN++: Exploiting visual-spatial relation for stereo-based 3D detectors. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)","DOI":"10.1109\/TPAMI.2022.3197236"},{"key":"3480_CR87","doi-asserted-by":"publisher","first-page":"102069","DOI":"10.1016\/j.aei.2023.102069","volume":"57","author":"C Tao","year":"2023","unstructured":"Tao, C., Cao, C., Cheng, H., et al.: An efficient 3D object detection method based on fast guided anchor stereo RCNN. Adv. Eng. Inform. 57, 102069 (2023)","journal-title":"Adv. Eng. Inform."},{"key":"3480_CR88","doi-asserted-by":"crossref","unstructured":"Kandelkar A, Batra I, Sharma S, et al.: Occlusion Problem in 3D Object Detection: A Review. In: Proceedings of the International Conference on Innovative Computing and Communications: Proceedings of ICICC 2022, Volume 1, Springer (2022)","DOI":"10.1007\/978-981-19-2821-5_26"},{"key":"3480_CR89","doi-asserted-by":"publisher","first-page":"126587","DOI":"10.1016\/j.neucom.2023.126587","volume":"553","author":"Y Tang","year":"2023","unstructured":"Tang, Y., He, H., Wang, Y., et al.: Multi-modality 3D object detection in autonomous driving: A review. Neurocomputing 553, 126587 (2023)","journal-title":"Neurocomputing"},{"key":"3480_CR90","unstructured":"Wang Y, Guizilini VC, Zhang T, et al.: Detr3d: 3d object detection from multi-view images via 3d-to-2d queries. In: Proceedings of the Conference on Robot Learning, PMLR (2022)"},{"key":"3480_CR91","unstructured":"Huang J, Huang G, Zhu Z, et al.: Bevdet: High-performance multi-camera 3d object detection in bird-eye-view (2021). arxiv:2112.11790"},{"key":"3480_CR92","doi-asserted-by":"crossref","unstructured":"Rukhovich D, Vorontsova A, Konushin A.: Imvoxelnet: Image to voxels projection for monocular and multi-view general-purpose 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (2022)","DOI":"10.1109\/WACV51458.2022.00133"},{"key":"3480_CR93","doi-asserted-by":"crossref","unstructured":"Liu Y, Wang T, Zhang X, et al.: Petr: Position embedding transformation for multi-view 3d object detection. In: Proceedings of the European Conference on Computer Vision, Springer (2022)","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"3480_CR94","doi-asserted-by":"crossref","unstructured":"Liu Y, Yan J, Jia F, et al.: Petrv2: A unified framework for 3d perception from multi-camera images. In: Proceedings of the Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"3480_CR95","doi-asserted-by":"crossref","unstructured":"Qi CR, Liu W, Wu C, et al.: Frustum pointnets for 3d object detection from rgb-d data. In: Proceedings of the Proceedings of the IEEE conference on computer vision and pattern recognition (2018)","DOI":"10.1109\/CVPR.2018.00102"},{"key":"3480_CR96","doi-asserted-by":"crossref","unstructured":"Xu D, Anguelov D, Jain A.: Pointfusion: Deep sensor fusion for 3d bounding box estimation.In: Proceedings of the Proceedings of the IEEE conference on computer vision and pattern recognition (2018)","DOI":"10.1109\/CVPR.2018.00033"},{"key":"3480_CR97","doi-asserted-by":"crossref","unstructured":"Wang Z, Jia K.: Frustum convnet: Sliding frustums to aggregate local point-wise features for amodal 3d object detection. In: Proceedings of the 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, (2019)","DOI":"10.1109\/IROS40897.2019.8968513"},{"key":"3480_CR98","doi-asserted-by":"crossref","unstructured":"Lu H, Chen X, Zhang G, et al.: SCANet: Spatial-channel attention network for 3D object detection. In: Proceedings of the ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, (2019)","DOI":"10.1109\/ICASSP.2019.8682746"},{"key":"3480_CR99","doi-asserted-by":"crossref","unstructured":"Liang M, Yang B, Chen Y, et al.: Multi-task multi-sensor fusion for 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00752"},{"key":"3480_CR100","doi-asserted-by":"crossref","unstructured":"Vora S, Lang AH, Helou B, et al.: Pointpainting: Sequential fusion for 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"3480_CR101","doi-asserted-by":"crossref","unstructured":"Yoo J H, Kim Y, Kim J, et al.: 3d-cvf: Generating joint camera and lidar features using cross-view spatial feature fusion for 3d object detection; proceedings of the Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXVII 16, Springer, (2020)","DOI":"10.1007\/978-3-030-58583-9_43"},{"key":"3480_CR102","doi-asserted-by":"crossref","unstructured":"Xie L, Xiang C, Yu Z, et al.: PI-RCNN: An efficient multi-sensor 3D object detector with point-based attentive cont-conv fusion module. In: Proceedings of the Proceedings of the AAAI conference on artificial intelligence (2020)","DOI":"10.1609\/aaai.v34i07.6933"},{"key":"3480_CR103","doi-asserted-by":"crossref","unstructured":"Huang T, Liu Z, Chen X, et al.: Epnet: Enhancing point features with image semantics for 3d object detection. In: Proceedings of the Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XV 16, Springer, (2020)","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"3480_CR104","doi-asserted-by":"crossref","unstructured":"Zhang Y, Chen J, Huang D.: Cat-det: Contrastively augmented transformer for multi-modal 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00098"},{"key":"3480_CR105","doi-asserted-by":"crossref","unstructured":"Gu J, Xiang Z, Zhao P, et al.: CVFNet: Real-time 3D object detection by learning cross view features. In: Proceedings of the 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE (2022)","DOI":"10.1109\/IROS47612.2022.9981087"},{"key":"3480_CR106","doi-asserted-by":"crossref","unstructured":"Bai X, Hu Z, Zhu X, et al.: Transfusion: Robust lidar-camera fusion for 3d object detection with transformers. In: Proceedings of the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"3480_CR107","doi-asserted-by":"crossref","unstructured":"Li Y, Yu AW, Meng T, et al.: Deepfusion: Lidar-camera deep fusion for multi-modal 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"3480_CR108","doi-asserted-by":"crossref","unstructured":"Liu Z, Tang H, Amini A, et al.: Bevfusion: Multi-task multi-sensor fusion with unified bird's-eye view representation. In: Proceedings of the 2023 IEEE international conference on robotics and automation (ICRA), IEEE, (2023)","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"3480_CR109","doi-asserted-by":"crossref","unstructured":"Jiao Y, Jie Z, Chen S, et al.: MSMDfusion: Fusing lidar and camera at multiple scales with multi-depth seeds for 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.02073"},{"key":"3480_CR110","doi-asserted-by":"crossref","unstructured":"Li X, Ma T, Hou Y, et al.: LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion. In: Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01681"},{"key":"3480_CR111","doi-asserted-by":"crossref","unstructured":"Wang H, Tang H, Shi S, et al.: UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation. In: Proceedings of the Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00625"},{"key":"3480_CR112","doi-asserted-by":"crossref","unstructured":"Chen Y, Yu Z, Chen Y, et al.: Focalformer3d: focusing on hard instance for 3d object detection. In: Proceedings of the Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00771"},{"key":"3480_CR113","unstructured":"HU H, WANG F, SU J, et al. EA-LSS: Edge-aware Lift-splat-shot Framework for 3D BEV Object Detection (2023). arxiv:2303.17895"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03480-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03480-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03480-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T14:54:46Z","timestamp":1739372086000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03480-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,14]]},"references-count":113,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["3480"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03480-6","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,14]]},"assertion":[{"value":"10 May 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 June 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflicts of interest\/competing interests to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}