{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T19:33:47Z","timestamp":1793129627202,"version":"4.5.0"},"reference-count":170,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,7,11]],"date-time":"2023-07-11T00:00:00Z","timestamp":1689033600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,7,11]],"date-time":"2023-07-11T00:00:00Z","timestamp":1689033600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001652","name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001652","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2024,3]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Strong demand for autonomous vehicles and the wide availability of 3D sensors are continuously fueling the proposal of novel methods for 3D object detection. In this paper, we provide a comprehensive survey of recent developments from 2012\u20132021 in 3D  object detection covering the full pipeline from input data, over data representation and feature extraction to the actual detection modules. We introduce fundamental concepts, focus on a broad range of different approaches that have emerged over the past decade, and propose a systematization that provides a practical framework for comparing these approaches with the goal of guiding future development, evaluation, and application activities. Specifically, our survey and systematization of 3D object detection models and methods can help researchers and practitioners to get a quick overview of the field by decomposing 3DOD solutions into more manageable pieces.<\/jats:p>","DOI":"10.1007\/s00371-023-02891-1","type":"journal-article","created":{"date-parts":[[2023,7,11]],"date-time":"2023-07-11T12:01:50Z","timestamp":1689076910000},"page":"1867-1913","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Survey and systematization of 3D object detection models and methods"],"prefix":"10.1007","volume":"40","author":[{"given":"Moritz","family":"Drobnitzky","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonas","family":"Friederich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4736-2397","authenticated-orcid":false,"given":"Bernhard","family":"Egger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1105-8086","authenticated-orcid":false,"given":"Patrick","family":"Zschech","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,7,11]]},"reference":[{"key":"2891_CR1","doi-asserted-by":"publisher","unstructured":"Ahmadyan, A., Zhang, L., Ablavatski, A., Wei, J., Grundmann, M.: Objectron: A large scale dataset of object-centric videos in the wild with pose annotations. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Nashville, TN, USA. pp. 7818\u20137827 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00773","DOI":"10.1109\/CVPR46437.2021.00773"},{"key":"2891_CR2","doi-asserted-by":"publisher","unstructured":"Ali, W., Abdelkarim, S., Zidan, M., Zahran, M., Sallab, A.E.: YOLO3D: End-to-end real-time 3D oriented object bounding box detection from LiDAR point cloud. In: Leal-Taix\u00e9, L., Roth, S. (Eds.), Computer Vision\u2014ECCV 2018 Workshops, Springer International Publishing. pp. 716\u2013728 (2019). https:\/\/doi.org\/10.1007\/978-3-030-11015-4_54","DOI":"10.1007\/978-3-030-11015-4_54"},{"key":"2891_CR3","doi-asserted-by":"publisher","unstructured":"Amirkhani, A., Karimi, M.P., Banitalebi-Dehkordi, A.: A survey on adversarial attacks and defenses for object detection and their applications in autonomous vehicles. Vis. Comput. (2022). https:\/\/doi.org\/10.1007\/s00371-022-02660-6","DOI":"10.1007\/s00371-022-02660-6"},{"key":"2891_CR4","doi-asserted-by":"publisher","unstructured":"Aprile, W.A., Ruffaldi, E., Sotgiu, E., Frisoli, A., Bergamasco, M.: A dynamically reconfigurable stereoscopic\/panoramic vision mobile robot head controlled from a virtual environment. Vis. Comput. 24, 941\u2013946 (2008). https:\/\/doi.org\/10.1007\/s00371-008-0278-0","DOI":"10.1007\/s00371-008-0278-0"},{"key":"2891_CR5","doi-asserted-by":"publisher","first-page":"3782","DOI":"10.1109\/TITS.2019.2892405","volume":"20","author":"E Arnold","year":"2019","unstructured":"Arnold, E., Al-Jarrah, O.Y., Dianati, M., Fallah, S., Oxtoby, D., Mouzakitis, A.: A survey on 3d object detection methods for autonomous driving applications. IEEE Trans. Intell. Transp. Syst. 20, 3782\u20133795 (2019). https:\/\/doi.org\/10.1109\/TITS.2019.2892405","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"2891_CR6","doi-asserted-by":"publisher","unstructured":"Barabanau, I., Artemov, A., Burnaev, E., Murashkin, V.: Monocular 3D object detection via geometric reasoning on keypoints. In: Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, SCITEPRESS\u2014Science and Technology Publications, Valletta, Malta. pp. 652\u2013659 (2020). https:\/\/doi.org\/10.5220\/0009102506520659","DOI":"10.5220\/0009102506520659"},{"key":"2891_CR7","doi-asserted-by":"publisher","unstructured":"Bayoudh, K., Knani, R., Hamdaoui, F., Mtibaa, A.: A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets. Vis. Comput. 38, 2939\u20132970 (2022) . https:\/\/doi.org\/10.1007\/s00371-021-02166-7","DOI":"10.1007\/s00371-021-02166-7"},{"key":"2891_CR8","doi-asserted-by":"publisher","first-page":"1729","DOI":"10.3390\/rs12111729","volume":"12","author":"SA Bello","year":"2020","unstructured":"Bello, S.A., Yu, S., Wang, C., Adam, J.M., Li, J.: Review: deep learning on 3D point clouds. Remote Sens. 12, 1729 (2020). https:\/\/doi.org\/10.3390\/rs12111729","journal-title":"Remote Sens."},{"key":"2891_CR9","doi-asserted-by":"publisher","unstructured":"Beltr\u00e1n, J., Guindel, C., Moreno, F.M., Cruzado, D., Garc\u00eda, F., De\u00a0La\u00a0Escalera, A.: BirdNet: A 3D object detection framework from LiDAR information. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp. 3517\u20133523 (2018). https:\/\/doi.org\/10.1109\/ITSC.2018.8569311","DOI":"10.1109\/ITSC.2018.8569311"},{"key":"2891_CR10","volume-title":"Pattern Recognition and Machine Learning","author":"CM Bishop","year":"2006","unstructured":"Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, Information science and statistics, Berlin (2006)"},{"key":"2891_CR11","doi-asserted-by":"publisher","unstructured":"Brazil, G., Liu, X.: M3D-RPN: Monocular 3D region proposal network for object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9286\u20139295 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00938","DOI":"10.1109\/ICCV.2019.00938"},{"key":"2891_CR12","doi-asserted-by":"publisher","unstructured":"Caesar, H., Bankiti, V., Lang, A.H., Vora, S., Liong, V.E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., Beijbom, O.: nuScenes: a multimodal dataset for autonomous driving. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Seattle, WA, USA. pp. 11618\u201311628 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01164","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"2891_CR13","doi-asserted-by":"publisher","unstructured":"Chabot, F., Chaouch, M., Rabarisoa, J., Teuliere, C., Chateau, T.: Deep MANTA: A coarse-to-fine many-task network for joint 2D and 3D vehicle analysis from monocular image. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Honolulu, HI. pp. 1827\u20131836 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.198","DOI":"10.1109\/CVPR.2017.198"},{"key":"2891_CR14","doi-asserted-by":"publisher","unstructured":"Chen, G., Qin, H.: Class-discriminative focal loss for extreme imbalanced multiclass object detection towards autonomous driving. Vis. Comput. 38, 1051\u20131063 (2022). https:\/\/doi.org\/10.1007\/s00371-021-02067-9","DOI":"10.1007\/s00371-021-02067-9"},{"key":"2891_CR15","doi-asserted-by":"publisher","unstructured":"Chen, Q., Tang, S., Yang, Q., Fu, S.: Cooper: cooperative perception for connected autonomous vehicles based on 3D point clouds. In: 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS), pp. 514\u2013524 (2019a). https:\/\/doi.org\/10.1109\/ICDCS.2019.00058","DOI":"10.1109\/ICDCS.2019.00058"},{"key":"2891_CR16","doi-asserted-by":"publisher","unstructured":"Chen, X., Kundu, K., Zhang, Z., Ma, H., Fidler, S., Urtasun, R.: Monocular 3D object detection for autonomous driving. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2147\u20132156 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.236","DOI":"10.1109\/CVPR.2016.236"},{"key":"2891_CR17","unstructured":"Chen, X., Kundu, K., Zhu, Y., Berneshawi, A.G., Ma, H., Fidler, S., Urtasun, R.: 3D Object Proposals for Accurate Object Class Detection, in: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (Eds.), Advances in Neural Information Processing Systems 28. Curran Associates, Inc., pp. 424\u2013432 (2015)"},{"key":"2891_CR18","doi-asserted-by":"publisher","first-page":"1259","DOI":"10.1109\/TPAMI.2017.2706685","volume":"40","author":"X Chen","year":"2018","unstructured":"Chen, X., Kundu, K., Zhu, Y., Ma, H., Fidler, S., Urtasun, R.: 3D object proposals using stereo imagery for accurate object class detection. IEEE Trans Pattern Anal Mach Intell 40, 1259\u20131272 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2706685","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2891_CR19","doi-asserted-by":"publisher","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3D object detection network for autonomous driving. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6526\u20136534 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.691","DOI":"10.1109\/CVPR.2017.691"},{"key":"2891_CR20","doi-asserted-by":"publisher","unstructured":"Chen, Y., Liu, S., Shen, X., Jia, J.: Fast point r-CNN, in: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE. pp. 9774\u20139783 (2019b). https:\/\/doi.org\/10.1109\/ICCV.2019.00987","DOI":"10.1109\/ICCV.2019.00987"},{"key":"2891_CR21","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1007\/978-3-031-19839-7_30","volume-title":"Computer Vision\u2014ECCV 2022","author":"Z Cheng","year":"2022","unstructured":"Cheng, Z., Liang, J., Choi, H., Tao, G., Cao, Z., Liu, D., Zhang, X.: Physical attack on monocular depth estimation with optimal adversarial patches. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision\u2014ECCV 2022, pp. 514\u2013532. Springer Nature Switzerland, Cham (2022)"},{"key":"2891_CR22","doi-asserted-by":"publisher","unstructured":"Crivellaro, A., Rad, M., Verdie, Y., Yi, K.M., Fua, P., Lepetit, V.: A Novel representation of parts for accurate 3D object detection and tracking in monocular images. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 4391\u20134399 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.499","DOI":"10.1109\/ICCV.2015.499"},{"key":"2891_CR23","doi-asserted-by":"publisher","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), IEEE. pp. 886\u2013893 (2005). https:\/\/doi.org\/10.1109\/CVPR.2005.177","DOI":"10.1109\/CVPR.2005.177"},{"key":"2891_CR24","unstructured":"Davies, E.R.: Computer and machine vision: theory, algorithms, practicalities. 4th ed., Elsevier (2012)"},{"key":"2891_CR25","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2891_CR26","doi-asserted-by":"publisher","first-page":"1201","DOI":"10.1609\/aaai.v35i2.16207","volume":"35","author":"J Deng","year":"2021","unstructured":"Deng, J., Shi, S., Li, P., Zhou, W., Zhang, Y., Li, H.: Voxel R-CNN: towards high performance voxel-based 3D object detection. Proceedings of the AAAI Conference on Artificial Intelligence 35, 1201\u20131209 (2021)","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2891_CR27","doi-asserted-by":"publisher","unstructured":"Deng, Z., Latecki, J.L.: Amodal Detection of 3D Objects: Inferring 3D bounding boxes from 2D ones in RGB-depth images. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 398\u2013406 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.50","DOI":"10.1109\/CVPR.2017.50"},{"key":"2891_CR28","doi-asserted-by":"publisher","unstructured":"Du, X., Ang, M.H., Karaman, S., Rus, D.: A general pipeline for 3d detection of vehicles. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), IEEE. pp. 3194\u20133200 (2018). https:\/\/doi.org\/10.1109\/ICRA.2018.8461232","DOI":"10.1109\/ICRA.2018.8461232"},{"key":"2891_CR29","doi-asserted-by":"publisher","unstructured":"Engelcke, M., Rao, D., Wang, D.Z., Tong, C.H., Posner, I.: Vote3Deep: Fast object detection in 3D point clouds using efficient convolutional neural networks. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 1355\u20131361 (2017). https:\/\/doi.org\/10.1109\/ICRA.2017.7989161","DOI":"10.1109\/ICRA.2017.7989161"},{"key":"2891_CR30","doi-asserted-by":"publisher","unstructured":"Ferguson, M., Law, K.: A 2D-3D object detection system for updating building information models with mobile robots. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1357\u20131365 (2019). https:\/\/doi.org\/10.1109\/WACV.2019.00149","DOI":"10.1109\/WACV.2019.00149"},{"key":"2891_CR31","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.inffus.2020.11.002","volume":"68","author":"D Fernandes","year":"2021","unstructured":"Fernandes, D., Silva, A., N\u00e9voa, R., Sim\u00f5es, C., Gonzalez, D., Guevara, M., Novais, P., Monteiro, J., Melo-Pinto, P.: Point-cloud based 3d object detection and classification methods for self-driving applications: a survey and taxonomy. Inf. Fusion 68, 161\u2013191 (2021). https:\/\/doi.org\/10.1016\/j.inffus.2020.11.002","journal-title":"Inf. Fusion"},{"key":"2891_CR32","unstructured":"Fidler, S., Dickinson, S., Urtasun, R.: 3D object detection and viewpoint estimation with a deformable 3D cuboid model. In: Proceedings of the 25th International Conference on Neural Information Processing Systems\u2014Volume 1, Curran Associates Inc., USA. pp. 611\u2013619 (2012)"},{"key":"2891_CR33","doi-asserted-by":"publisher","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM24, pp. 381\u2013395 (1981). https:\/\/doi.org\/10.1145\/358669.358692","DOI":"10.1145\/358669.358692"},{"key":"2891_CR34","doi-asserted-by":"publisher","unstructured":"Friederich, J., Zschech, P.: Review and systematization of solutions for 3d object detection. In: 2020 15th International Conference on Wirtschaftsinformatik (WI), pp. 1699\u20131711 (2020). https:\/\/doi.org\/10.30844\/wi_2020_r2-friedrich","DOI":"10.30844\/wi_2020_r2-friedrich"},{"key":"2891_CR35","doi-asserted-by":"publisher","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K., Tao, D.: Deep ordinal regression network for monocular depth estimation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2002\u20132011 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00214","DOI":"10.1109\/CVPR.2018.00214"},{"key":"2891_CR36","doi-asserted-by":"publisher","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361 (2012). https:\/\/doi.org\/10.1109\/CVPR.2012.6248074","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"2891_CR37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-91761-0","volume-title":"A Survey on 3D Cameras: Metrological Comparison of Time-of-Flight","author":"S Giancola","year":"2018","unstructured":"Giancola, S., Valenti, M., Sala, R.: A Survey on 3D Cameras: Metrological Comparison of Time-of-Flight. SpringerBriefs in Computer Science, Springer International Publishing, Structured-Light and Active Stereoscopy Technologies, Berlin (2018). https:\/\/doi.org\/10.1007\/978-3-319-91761-0"},{"key":"2891_CR38","doi-asserted-by":"publisher","unstructured":"Girshick, R.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1440\u20131448 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"2891_CR39","doi-asserted-by":"publisher","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, IEEE. pp. 580\u2013587 (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.81","DOI":"10.1109\/CVPR.2014.81"},{"key":"2891_CR40","doi-asserted-by":"publisher","unstructured":"Godard, C., Aodha, O.M., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6602\u20136611 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.699","DOI":"10.1109\/CVPR.2017.699"},{"key":"2891_CR41","doi-asserted-by":"crossref","unstructured":"Graham, B.: Spatially-sparse convolutional neural networks (2014). arXiv:1409.6070 [cs]","DOI":"10.5244\/C.29.150"},{"key":"2891_CR42","doi-asserted-by":"publisher","unstructured":"Graham, B.: Sparse 3D convolutional neural networks. In: Procedings of the British Machine Vision Conference 2015, British Machine Vision Association, Swansea. pp. 150.1\u2013150.9 (2015). https:\/\/doi.org\/10.5244\/C.29.150","DOI":"10.5244\/C.29.150"},{"key":"2891_CR43","doi-asserted-by":"publisher","unstructured":"Graham, B., Engelcke, M., Maaten, L.v.d.: 3D Semantic segmentation with submanifold sparse convolutional networks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9224\u20139232 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00961","DOI":"10.1109\/CVPR.2018.00961"},{"key":"2891_CR44","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.3390\/rs11121499","volume":"11","author":"D Griffiths","year":"2019","unstructured":"Griffiths, D., Boehm, J.: A review on deep learning techniques for 3D sensed data classification. Remote Sens. 11, 1499 (2019). https:\/\/doi.org\/10.3390\/rs11121499","journal-title":"Remote Sens."},{"key":"2891_CR45","doi-asserted-by":"publisher","first-page":"4338","DOI":"10.1109\/TPAMI.2020.3005434","volume":"43","author":"Y Guo","year":"2021","unstructured":"Guo, Y., Wang, H., Hu, Q., Liu, H., Liu, L., Bennamoun, M.: Deep learning for 3D point clouds: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 43, 4338\u20134364 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2020.3005434","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2891_CR46","doi-asserted-by":"publisher","unstructured":"Gupta, I., Rangesh, A., Trivedi, M.: 3D bounding boxes for road vehicles: a one-stage, localization prioritized approach using single monocular images. In: Leal-Taix\u00e9, L., Roth, S. (Eds.), Computer vision\u2014ECCV 2018 workshops. Springer International Publishing, Cham. volume11133 of Lecture Notes in Computer Science, pp. 626\u2013641 (2019). https:\/\/doi.org\/10.1007\/978-3-030-11021-5_39","DOI":"10.1007\/978-3-030-11021-5_39"},{"key":"2891_CR47","doi-asserted-by":"publisher","unstructured":"Gustafsson, F.K., Danelljan, M., Schon, T.B.: Accurate 3D object detection using energy-based models. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE, Nashville, TN, USA. pp. 2849\u20132858 (2021). https:\/\/doi.org\/10.1109\/CVPRW53098.2021.00320","DOI":"10.1109\/CVPRW53098.2021.00320"},{"key":"2891_CR48","doi-asserted-by":"publisher","unstructured":"He, C., Zeng, H., Huang, J., Hua, X.S., Zhang, L.: Structure aware single-stage 3D object detection from point cloud. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE. pp. 11870\u201311879 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01189","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"2891_CR49","doi-asserted-by":"publisher","unstructured":"He, R., Rojas, J., Guan, Y.: A 3D object detection and pose estimation pipeline using RGB-D images. In: 2017 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 1527\u20131532 (2017). https:\/\/doi.org\/10.1109\/ROBIO.2017.8324634","DOI":"10.1109\/ROBIO.2017.8324634"},{"key":"2891_CR50","doi-asserted-by":"publisher","unstructured":"Hinterstoisser, S., Holzer, S., Cagniart, C., Ilic, S., Konolige, K., Navab, N., Lepetit, V.: Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes. In: 2011 International Conference on Computer Vision, IEEE. pp. 858\u2013865 (2011). https:\/\/doi.org\/10.1109\/ICCV.2011.6126326","DOI":"10.1109\/ICCV.2011.6126326"},{"key":"2891_CR51","unstructured":"Huang, S., Qi, S., Xiao, Y., Zhu, Y., Wu, Y.N., Zhu, S.C.: Cooperative holistic scene understanding: unifying 3D object, layout, and camera pose estimation. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, Curran Associates Inc., USA. pp. 206\u2013217 (2018)"},{"key":"2891_CR52","doi-asserted-by":"publisher","unstructured":"Huang, T., Liu, Z., Chen, X., Bai, X.: EPNet: Enhancing point features with image semantics for 3D object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (Eds.), Computer Vision - ECCV 2020. Springer International Publishing, Cham, volume12360, pp. 35\u201352 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_3","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"2891_CR53","doi-asserted-by":"publisher","unstructured":"Huang, Y., Chen, Y.: Survey of state-of-art autonomous driving technologies with deep learning. In: 2020 IEEE 20th International Conference on Software Quality, Reliability and Security Companion (QRS-C), IEEE. pp. 221\u2013228 (2020). https:\/\/doi.org\/10.1109\/QRS-C51114.2020.00045","DOI":"10.1109\/QRS-C51114.2020.00045"},{"key":"2891_CR54","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1007\/s12525-021-00475-2","volume":"31","author":"C Janiesch","year":"2021","unstructured":"Janiesch, C., Zschech, P., Heinrich, K.: Machine learning and deep learning. Electronic Markets 31, 685\u2013695 (2021). https:\/\/doi.org\/10.1007\/s12525-021-00475-2","journal-title":"Electronic Markets"},{"key":"2891_CR55","doi-asserted-by":"publisher","unstructured":"Ji, C., Liu, G., Zhao, D.: Stereo 3D object detection via instance depth prior guidance and adaptive spatial feature aggregation. Vis. Comput. (2022) https:\/\/doi.org\/10.1007\/s00371-022-02607-x","DOI":"10.1007\/s00371-022-02607-x"},{"key":"2891_CR56","unstructured":"J\u00f6rgensen, E., Zach, C., Kahl, F.: Monocular 3D object detection and box fitting trained end-to-end using intersection-over-union loss (2019). arXiv:1906.08070 [cs] , pp. 1\u201310"},{"key":"2891_CR57","doi-asserted-by":"publisher","unstructured":"Kehl, W., Milletari, F., Tombari, F., Ilic, S., Navab, N.: Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimation, in: Leibe, B., Matas, J., Sebe, N., Welling, M. (Eds.), Computer Vision\u2014ECCV 2016. Springer International Publishing. pp. 205\u2013220 (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_13","DOI":"10.1007\/978-3-319-46487-9_13"},{"key":"2891_CR58","doi-asserted-by":"publisher","unstructured":"Kim, J.U., Kang, H.: LiDAR based 3D object detection using CCD information. In: 2017 IEEE Third International Conference on Multimedia Big Data (BigMM), pp. 303\u2013309 (2017). https:\/\/doi.org\/10.1109\/BigMM.2017.59","DOI":"10.1109\/BigMM.2017.59"},{"key":"2891_CR59","unstructured":"KITTI.: Kitti 3dod benchmark (2021). http:\/\/www.cvlibs.net\/datasets\/kitti\/eval_object.php?obj_benchmark=3d"},{"key":"2891_CR60","doi-asserted-by":"publisher","unstructured":"Ku, J., Mozifian, M., Lee, J., Harakeh, A., Waslander, S.L.: Joint 3D proposal generation and object detection from view aggregation. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1\u20138 (2018). https:\/\/doi.org\/10.1109\/IROS.2018.8594049","DOI":"10.1109\/IROS.2018.8594049"},{"key":"2891_CR61","doi-asserted-by":"publisher","unstructured":"Ku, J., Pon, A.D., Waslander, S.L.: Monocular 3D object detection leveraging accurate proposals and shape reconstruction. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11859\u201311868 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.01214","DOI":"10.1109\/CVPR.2019.01214"},{"key":"2891_CR62","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., Zhang, M., Zhang, Z.: Voxel-FPN: Multi-scale voxel feature aggregation for 3d object detection from LIDAR point clouds. Sensors 20, 704 (2020). https:\/\/doi.org\/10.3390\/s20030704","journal-title":"Sensors"},{"key":"2891_CR63","doi-asserted-by":"publisher","unstructured":"Payen\u00a0de La\u00a0Garanderie, G., Atapour\u00a0Abarghouei, A., Breckon, T.P.: Eliminating the blind spot: adapting 3D object detection and monocular depth estimation to 360$$^\\circ $$ panoramic imagery. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (Eds.), Computer Vision - ECCV 2018, Springer International Publishing, Cham, pp. 812\u2013830 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_48","DOI":"10.1007\/978-3-030-01261-8_48"},{"key":"2891_CR64","doi-asserted-by":"publisher","unstructured":"Lahoud, J., Ghanem, B.: 2D-Driven 3D object detection in RGB-D images. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 4632\u20134640 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.495","DOI":"10.1109\/ICCV.2017.495"},{"key":"2891_CR65","doi-asserted-by":"publisher","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: PointPillars: Fast encoders for object detection from point clouds. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE. pp. 12689\u201312697 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.01298","DOI":"10.1109\/CVPR.2019.01298"},{"key":"2891_CR66","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436\u2013444 (2015). https:\/\/doi.org\/10.1038\/nature14539","journal-title":"Nature"},{"key":"2891_CR67","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1641\/0006-3568(2002)052[0019:LRSFES]2.0.CO;2","volume":"52","author":"MA Lefsky","year":"2002","unstructured":"Lefsky, M.A., Cohen, W.B., Parker, G.G., Harding, D.J.: Lidar remote sensing for ecosystem studies. BioScience 52, 19 (2002). https:\/\/doi.org\/10.1641\/0006-3568(2002)052[0019:LRSFES]2.0.CO;2","journal-title":"BioScience"},{"key":"2891_CR68","unstructured":"Lehner, J., Mitterecker, A., Adler, T., Hofmarcher, M., Nessler, B., Hochreiter, S.: Patch refinement\u2014localized 3d object detection (2019). arXiv:1910.04093 [cs]"},{"key":"2891_CR69","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1007\/s11263-007-0095-3","volume":"77","author":"B Leibe","year":"2008","unstructured":"Leibe, B., Leonardis, A., Schiele, B.: Robust object detection with interleaved categorization and segmentation. Int. J. Comput. Vis. 77, 259\u2013289 (2008). https:\/\/doi.org\/10.1007\/s11263-007-0095-3","journal-title":"Int. J. Comput. Vis."},{"key":"2891_CR70","doi-asserted-by":"publisher","unstructured":"Li, B.: 3d fully convolutional network for vehicle detection in point cloud. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE. pp. 1513\u20131518 (2017). https:\/\/doi.org\/10.1109\/IROS.2017.8205955","DOI":"10.1109\/IROS.2017.8205955"},{"key":"2891_CR71","doi-asserted-by":"publisher","unstructured":"Li, B., Ouyang, W., Sheng, L., Zeng, X., Wang, X.: GS3D: An efficient 3D object detection framework for autonomous driving. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1019\u20131028 (2019a). https:\/\/doi.org\/10.1109\/CVPR.2019.00111","DOI":"10.1109\/CVPR.2019.00111"},{"key":"2891_CR72","doi-asserted-by":"publisher","unstructured":"Li, B., Zhang, T., Xia, T.: Vehicle detection from 3d lidar using fully convolutional network. In: Robotics: Science and Systems XII, Robotics: Science and Systems Foundation. pp. 1\u20138 (2016). https:\/\/doi.org\/10.15607\/RSS.2016.XII.042","DOI":"10.15607\/RSS.2016.XII.042"},{"key":"2891_CR73","unstructured":"Li, J., Luo, S., Zhu, Z., Dai, H., Krylov, A.S., Ding, Y., Shao, L.: 3d IoU-net: IoU guided 3d object detector for point clouds (2020). arXiv:2004.04962 [cs]"},{"key":"2891_CR74","doi-asserted-by":"publisher","first-page":"1434","DOI":"10.3390\/s19061434","volume":"19","author":"M Li","year":"2019","unstructured":"Li, M., Hu, Y., Zhao, N., Qian, Q.: One-stage multi-sensor data fusion convolutional neural network for 3d object detection. Sensors 19, 1434 (2019). https:\/\/doi.org\/10.3390\/s19061434","journal-title":"Sensors"},{"key":"2891_CR75","doi-asserted-by":"publisher","unstructured":"Li, P., Chen, X., Shen, S.: Stereo R-CNN Based 3D object detection for autonomous driving. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7636\u20137644 (2019c). https:\/\/doi.org\/10.1109\/CVPR.2019.00783","DOI":"10.1109\/CVPR.2019.00783"},{"key":"2891_CR76","doi-asserted-by":"publisher","unstructured":"Li, S., Yang, L., Huang, J., Hua, X.S., Zhang, L.: Dynamic anchor feature selection for single-shot object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6608\u20136617 (2019d). https:\/\/doi.org\/10.1109\/ICCV.2019.00671","DOI":"10.1109\/ICCV.2019.00671"},{"key":"2891_CR77","unstructured":"Li, X., Guivant, J.E., Kwok, N., Xu, Y.: 3D backbone network for 3D object detection (2019e). arXiv:1901.08373 [cs]"},{"key":"2891_CR78","doi-asserted-by":"publisher","unstructured":"Liang, J., Wang, Y., Chen, Y., Yang, B., Liu, D.: A triangulation-based visual localization for field robots. IEEE\/CAA J. Auto. Sin. 9, 1083\u20131086 (2022). https:\/\/doi.org\/10.1109\/JAS.2022.105632. conference Name: IEEE\/CAA Journal of Automatica Sinica","DOI":"10.1109\/JAS.2022.105632"},{"key":"2891_CR79","doi-asserted-by":"publisher","unstructured":"Liang, M., Yang, B., Chen, Y., Hu, R., Urtasun, R.: Multi-task multi-sensor fusion for 3d object detection. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE. pp. 7337\u20137345 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00752","DOI":"10.1109\/CVPR.2019.00752"},{"key":"2891_CR80","doi-asserted-by":"publisher","unstructured":"Liang, M., Yang, B., Wang, S., Urtasun, R.: Deep Continuous Fusion for Multi-sensor 3D Object Detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (Eds.), Computer Vision\u2014ECCV 2018, Springer International Publishing. pp. 663\u2013678 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_39","DOI":"10.1007\/978-3-030-01270-0_39"},{"key":"2891_CR81","unstructured":"Liang, Z., Zhang, M., Zhang, Z., Zhao, X., Pu, S.: RangeRCNN: Towards fast and accurate 3d object detection with range image representation (2020). arXiv:2009.00206 [cs]"},{"key":"2891_CR82","doi-asserted-by":"publisher","unstructured":"Liu, D., Cui, Y., Yan, L., Mousas, C., Yang, B., Chen, Y.: DenserNet: Weakly supervised visual localization using multi-scale feature aggregation. In: Proceedings of the AAAI Conference on Artificial Intelligence 35, 6101\u20136109 (2021). https:\/\/doi.org\/10.1609\/aaai.v35i7.16760. number. 7","DOI":"10.1609\/aaai.v35i7.16760"},{"key":"2891_CR83","doi-asserted-by":"publisher","unstructured":"Liu, J., Chen, H., Li, J.: Faster 3D object detection in RGB-D image using 3D selective search and object pruning. In: 2018 Chinese Control And Decision Conference (CCDC), pp. 4862\u20134866 (2018a). https:\/\/doi.org\/10.1109\/CCDC.2018.8407973","DOI":"10.1109\/CCDC.2018.8407973"},{"key":"2891_CR84","doi-asserted-by":"publisher","unstructured":"Liu, L., Lu, J., Xu, C., Tian, Q., Zhou, J.: Deep fitting degree scoring network for monocular 3D object detection. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1057\u20131066 (2019a). https:\/\/doi.org\/10.1109\/CVPR.2019.00115","DOI":"10.1109\/CVPR.2019.00115"},{"key":"2891_CR85","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","volume":"128","author":"L Liu","year":"2020","unstructured":"Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., Pietik\u00e4inen, M.: Deep learning for generic object detection: a survey. Int. J. Comput. Vis. 128, 261\u2013318 (2020). https:\/\/doi.org\/10.1007\/s11263-019-01247-4","journal-title":"Int. J. Comput. Vis."},{"key":"2891_CR86","doi-asserted-by":"publisher","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: SSD: Single Shot MultiBox Detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (Eds.), Computer Vision\u2014ECCV 2016, Springer International Publishing, Cham. pp. 21\u201337 (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2891_CR87","doi-asserted-by":"publisher","first-page":"4188","DOI":"10.3390\/s19194188","volume":"19","author":"W Liu","year":"2019","unstructured":"Liu, W., Sun, J., Li, W., Hu, T., Wang, P.: Deep learning on point clouds and its application: a survey. Sensors 19, 4188 (2019). https:\/\/doi.org\/10.3390\/s19194188","journal-title":"Sensors"},{"key":"2891_CR88","doi-asserted-by":"publisher","unstructured":"Liu, Y., Xu, Y., Li, S.b.: 2-D human pose estimation from images based on deep learning: a review. In: 2018 2nd IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference (IMCEC), IEEE, Xi\u2019an. pp. 462\u2013465 (2018b). https:\/\/doi.org\/10.1109\/IMCEC.2018.8469573","DOI":"10.1109\/IMCEC.2018.8469573"},{"key":"2891_CR89","doi-asserted-by":"publisher","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431\u20133440 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298965","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2891_CR90","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60, 91\u2013110 (2004). https:\/\/doi.org\/10.1023\/B:VISI.0000029664.99615.94","journal-title":"Int. J. Comput. Vis."},{"key":"2891_CR91","doi-asserted-by":"publisher","unstructured":"Lu, H., Chen, X., Zhang, G., Zhou, Q., Ma, Y., Zhao, Y.: Scanet: spatial-channel attention network for 3D object detection. In: ICASSP 2019\u20142019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1992\u20131996 (2019). https:\/\/doi.org\/10.1109\/ICASSP.2019.8682746","DOI":"10.1109\/ICASSP.2019.8682746"},{"key":"2891_CR92","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1016\/j.neucom.2019.10.025","volume":"378","author":"Q Luo","year":"2020","unstructured":"Luo, Q., Ma, H., Tang, L., Wang, Y., Xiong, R.: 3D-SSD: learning hierarchical features from RGB-D images for amodal 3D object detection. Neurocomputing 378, 364\u2013374 (2020). https:\/\/doi.org\/10.1016\/j.neucom.2019.10.025","journal-title":"Neurocomputing"},{"key":"2891_CR93","doi-asserted-by":"publisher","unstructured":"Ma, X., Wang, Z., Li, H., Zhang, P., Ouyang, W., Fan, X.: Accurate monocular 3D object detection via color-embedded 3D reconstruction for autonomous driving. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6850\u20136859 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00695","DOI":"10.1109\/ICCV.2019.00695"},{"key":"2891_CR94","doi-asserted-by":"publisher","unstructured":"Maisano, R., Tomaselli, V., Capra, A., Longo, F., Puliafito, A.: Reducing complexity of 3D indoor object detection. In: 2018 IEEE 4th International Forum on Research and Technology for Society and Industry (RTSI), pp. 1\u20136 (2018). https:\/\/doi.org\/10.1109\/RTSI.2018.8548514","DOI":"10.1109\/RTSI.2018.8548514"},{"key":"2891_CR95","doi-asserted-by":"crossref","unstructured":"Mao, J., Xue, Y., Niu, M., Bai, H., Feng, J., Liang, X., Xu, H., Xu, C.: Voxel transformer for 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3164\u20133173 (2021). https:\/\/openaccess.thecvf.com\/content\/ICCV2021\/html\/Mao_Voxel_Transformer_for_3D_Object_Detection_ICCV_2021_paper.html","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"2891_CR96","doi-asserted-by":"publisher","unstructured":"Meyer, G.P., Charland, J., Hegde, D., Laddha, A., Vallespi-Gonzalez, C.: Sensor fusion for joint 3D object detection and semantic segmentation. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1230\u20131237 (2019a). https:\/\/doi.org\/10.1109\/CVPRW.2019.00162","DOI":"10.1109\/CVPRW.2019.00162"},{"key":"2891_CR97","doi-asserted-by":"publisher","unstructured":"Meyer, G.P., Laddha, A., Kee, E., Vallespi-Gonzalez, C., Wellington, C.K.: LaserNet: an efficient probabilistic 3D object detector for autonomous driving. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12669\u201312678 (2019b). https:\/\/doi.org\/10.1109\/CVPR.2019.01296","DOI":"10.1109\/CVPR.2019.01296"},{"key":"2891_CR98","doi-asserted-by":"crossref","unstructured":"Misra, I., Girdhar, R., Joulin, A.: An end-to-end transformer model for 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2906\u20132917 (2021). https:\/\/openaccess.thecvf.com\/content\/ICCV2021\/html\/Misra_An_End-to-End_Transformer_Model_for_3D_Object_Detection_ICCV_2021_paper.html?ref=https:\/\/githubhelp.com","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"2891_CR99","doi-asserted-by":"publisher","unstructured":"Mousavian, A., Anguelov, D., Flynn, J., Ko\u0161eck\u00e1, J.: 3D bounding box estimation using deep learning and geometry. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5632\u20135640 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.597","DOI":"10.1109\/CVPR.2017.597"},{"key":"2891_CR100","doi-asserted-by":"publisher","unstructured":"Naiden, A., Paunescu, V., Kim, G., Jeon, B., Leordeanu, M.: Shift R-CNN: deep monocular 3D object detection with closed-form geometric constraints. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 61\u201365 (2019). https:\/\/doi.org\/10.1109\/ICIP.2019.8803397","DOI":"10.1109\/ICIP.2019.8803397"},{"key":"2891_CR101","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.3390\/ijgi2041038","volume":"2","author":"J Otepka","year":"2013","unstructured":"Otepka, J., Ghuffar, S., Waldhauser, C., Hochreiter, R., Pfeifer, N.: Georeferenced point clouds: a survey of features and point cloud management. ISPRS Int. J. Geo Inf. 2, 1038\u20131065 (2013). https:\/\/doi.org\/10.3390\/ijgi2041038","journal-title":"ISPRS Int. J. Geo Inf."},{"key":"2891_CR102","doi-asserted-by":"publisher","unstructured":"Pamplona, J., Madrigal, C., de\u00a0la Escalera, A.: PointNet evaluation for on-road object detection using a multi-resolution conditioning. In: Vera-Rodriguez, R., Fierrez, J., Morales, A. (Eds.), Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, Springer International Publishing. pp. 513\u2013520 (2019). https:\/\/doi.org\/10.1007\/978-3-030-13469-3_60","DOI":"10.1007\/978-3-030-13469-3_60"},{"key":"2891_CR103","doi-asserted-by":"crossref","unstructured":"Pan, X., Xia, Z., Song, S., Li, L.E., Huang, G.: 3D object detection With pointformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7463\u20137472 (2021). https:\/\/openaccess.thecvf.com\/content\/CVPR2021\/html\/Pan_3D_Object_Detection_With_Pointformer_CVPR_2021_paper.html","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"2891_CR104","doi-asserted-by":"publisher","unstructured":"Pang, S., Morris, D., Radha, H.: CLOCs: camera-LiDAR object candidates fusion for 3D object detection. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Las Vegas, NV, USA. pp. 10386\u201310393 (2020). https:\/\/doi.org\/10.1109\/IROS45743.2020.9341791","DOI":"10.1109\/IROS45743.2020.9341791"},{"key":"2891_CR105","doi-asserted-by":"publisher","unstructured":"Qi, C.R., Chen, X., Litany, O., Guibas, L.J.: ImVoteNet: boosting 3D object detection in point clouds with image votes. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Seattle, WA, USA. pp. 4403\u20134412 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00446","DOI":"10.1109\/CVPR42600.2020.00446"},{"key":"2891_CR106","doi-asserted-by":"publisher","unstructured":"Qi, C.R., Hao, S., Mo, K., Leonidas, J.G.: PointNet: deep learning on point sets for 3D classification and segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Honolulu, HI. pp. 77\u201385 (2017a). https:\/\/doi.org\/10.1109\/CVPR.2017.16","DOI":"10.1109\/CVPR.2017.16"},{"key":"2891_CR107","doi-asserted-by":"publisher","unstructured":"Qi, C.R., Litany, O., He, K., Guibas, L.: Deep hough voting for 3D object detection in point clouds. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9276\u20139285 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00937","DOI":"10.1109\/ICCV.2019.00937"},{"key":"2891_CR108","doi-asserted-by":"publisher","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointNets for 3D object detection from RGB-D Data. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 918\u2013927 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00102","DOI":"10.1109\/CVPR.2018.00102"},{"key":"2891_CR109","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: Deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems, Curran Associates, Inc.. pp. 1\u201310 (2017b)"},{"key":"2891_CR110","doi-asserted-by":"publisher","first-page":"8851","DOI":"10.1609\/aaai.v33i01.33018851","volume":"33","author":"Z Qin","year":"2019","unstructured":"Qin, Z., Wang, J., Lu, Y.: MonoGRNet: a geometric reasoning network for monocular 3d object localization. Proc. AAAI Conf. Artif. Intell. 33, 8851\u20138858 (2019). https:\/\/doi.org\/10.1609\/aaai.v33i01.33018851","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"2891_CR111","doi-asserted-by":"publisher","unstructured":"Qin, Z., Wang, J., Lu, Y.: Triangulation learning network: from monocular to stereo 3D object detection. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7607\u20137615 (2019b). https:\/\/doi.org\/10.1109\/CVPR.2019.00780","DOI":"10.1109\/CVPR.2019.00780"},{"key":"2891_CR112","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/j.ins.2018.09.040","volume":"476","author":"MM Rahman","year":"2019","unstructured":"Rahman, M.M., Tan, Y., Xue, J., Shao, L., Lu, K.: 3d object detection: learning 3d bounding boxes from scaled down 2d bounding boxes in RGB-d images. Inf. Sci. 476, 147\u2013158 (2019). https:\/\/doi.org\/10.1016\/j.ins.2018.09.040","journal-title":"Inf. Sci."},{"key":"2891_CR113","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE. pp. 779\u2013788 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"2891_CR114","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137\u20131149 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2891_CR115","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.jvcir.2018.05.019","volume":"55","author":"Y Ren","year":"2018","unstructured":"Ren, Y., Chen, C., Li, S., Kuo, C.C.J.: Context-assisted 3D (C3D) object detection from RGB-D images. J. Vis. Commun. Image Rep. 55, 131\u2013141 (2018). https:\/\/doi.org\/10.1016\/j.jvcir.2018.05.019","journal-title":"J. Vis. Commun. Image Rep."},{"key":"2891_CR116","doi-asserted-by":"publisher","unstructured":"Ren, Z., Sudderth, E.B.: Three-dimensional object detection and layout prediction using clouds of oriented gradients. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1525\u20131533 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.169","DOI":"10.1109\/CVPR.2016.169"},{"key":"2891_CR117","doi-asserted-by":"publisher","unstructured":"Ren, Z., Sudderth, E.B.: 3D object detection with latent support surfaces. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 937\u2013946 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00104","DOI":"10.1109\/CVPR.2018.00104"},{"key":"2891_CR118","doi-asserted-by":"publisher","first-page":"2670","DOI":"10.1109\/TPAMI.2019.2923201","volume":"42","author":"Z Ren","year":"2020","unstructured":"Ren, Z., Sudderth, E.B.: Clouds of oriented gradients for 3D detection of objects, surfaces, and indoor scene layouts. IEEE Trans. Pattern Anal. Mach. Intell. 42, 2670\u20132683 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2019.2923201","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2891_CR119","unstructured":"Roddick, T., Kendall, A., Cipolla, R.: Orthographic feature transform for monocular 3D object detection (2018). arXiv:1811.08188 [cs]"},{"key":"2891_CR120","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1080\/2573234X.2021.1908861","volume":"4","author":"C Sager","year":"2021","unstructured":"Sager, C., Janiesch, C., Zschech, P.: A survey of image labelling for computer vision applications. J. Bus. Anal. 4, 91\u2013110 (2021). https:\/\/doi.org\/10.1080\/2573234X.2021.1908861","journal-title":"J. Bus. Anal."},{"key":"2891_CR121","doi-asserted-by":"publisher","unstructured":"Sager, C., Zschech, P., Kuhl, N.: labelCloud: A lightweight domain-independent labeling tool for 3D object detection in point clouds. In: CAD\u201921 Proceedings, CAD Solutions LLC. pp. 319\u2013323 (2021b). http:\/\/www.cad-conference.net\/files\/CAD21\/CAD21_319-323.pdf, https:\/\/doi.org\/10.14733\/cadconfP.2021.319-323","DOI":"10.14733\/cadconfP.2021.319-323"},{"key":"2891_CR122","doi-asserted-by":"publisher","unstructured":"Shen, X., Stamos, I.: Frustum VoxNet for 3d object detection from RGB-d or depth images. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE. pp. 1687\u20131695 (2020). https:\/\/doi.org\/10.1109\/WACV45572.2020.9093276","DOI":"10.1109\/WACV45572.2020.9093276"},{"key":"2891_CR123","doi-asserted-by":"publisher","unstructured":"Shi, S., Guo, C., Jiang, L., Wang, Z., Shi, J., Wang, X., Li, H.: PV-RCNN: Point-voxel feature set abstraction for 3D object detection. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Seattle, WA, USA. pp. 10526\u201310535 (2020a). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01054","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"2891_CR124","doi-asserted-by":"publisher","unstructured":"Shi, S., Wang, X., Li, H.: PointRCNN: 3D object proposal generation and detection from point cloud. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013779 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00086","DOI":"10.1109\/CVPR.2019.00086"},{"key":"2891_CR125","doi-asserted-by":"publisher","unstructured":"Shi, S., Wang, Z., Shi, J., Wang, X., Li, H.: From points to parts: 3D object detection from point cloud with part-aware and part-aggregation network. IEEE Trans. Pattern Anal. Mach. Intell., pp. 1\u20131,(2020). https:\/\/doi.org\/10.1109\/TPAMI.2020.2977026","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"2891_CR126","doi-asserted-by":"publisher","unstructured":"Shi, W., Rajkumar, R.: Point-GNN: graph neural network for 3D object detection in a point cloud. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Seattle, WA, USA. pp. 1708\u20131716 (2020). https:\/\/ieeexplore.ieee.org\/document\/9156733\/, https:\/\/doi.org\/10.1109\/CVPR42600.2020.00178","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"2891_CR127","doi-asserted-by":"publisher","unstructured":"Shin, K., Kwon, Y.P., Tomizuka, M.: RoarNet: A Robust 3D object detection based on region approximation refinement. In: 2019 IEEE Intelligent Vehicles Symposium (IV), pp. 2510\u20132515 (2019). https:\/\/doi.org\/10.1109\/IVS.2019.8813895","DOI":"10.1109\/IVS.2019.8813895"},{"key":"2891_CR128","doi-asserted-by":"publisher","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (Eds.), Computer Vision\u2014ECCV 2012, Springer, Berlin, Heidelberg. pp. 746\u2013760 (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"2891_CR129","doi-asserted-by":"publisher","unstructured":"Simon, M., Amende, K., Kraus, A., Honer, J., Samann, T., Kaulbersch, H., Milz, S., Gross, H.M.: Complexer-YOLO: Real-time 3D object detection and tracking on semantic point clouds. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE, Long Beach, CA, USA. pp. 1190\u20131199 (2019a). https:\/\/doi.org\/10.1109\/CVPRW.2019.00158","DOI":"10.1109\/CVPRW.2019.00158"},{"key":"2891_CR130","doi-asserted-by":"publisher","unstructured":"Simon, M., Milz, S., Amende, K., Gross, H.M.: Complex-YOLO: An Euler-region-proposal for real-time 3D object detection on point clouds. In: Leal-Taix\u00e9, L., Roth, S. (Eds.), Computer Vision\u2014ECCV 2018 Workshops, Springer International Publishing. pp. 197\u2013209 (2019b). https:\/\/doi.org\/10.1007\/978-3-030-11009-3_11","DOI":"10.1007\/978-3-030-11009-3_11"},{"key":"2891_CR131","doi-asserted-by":"publisher","unstructured":"Simonelli, A., Bul\u00f2, S.R., Porzi, L., Lopez-Antequera, M., Kontschieder, P.: Disentangling monocular 3D object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1991\u20131999 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00208","DOI":"10.1109\/ICCV.2019.00208"},{"key":"2891_CR132","doi-asserted-by":"publisher","unstructured":"Sindagi, V.A., Zhou, Y., Tuzel, O.: MVX-Net: multimodal VoxelNet for 3D object detection. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 7276\u20137282 (2019). https:\/\/doi.org\/10.1109\/ICRA.2019.8794195","DOI":"10.1109\/ICRA.2019.8794195"},{"key":"2891_CR133","doi-asserted-by":"publisher","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: SUN RGB-D: a RGB-D scene understanding benchmark suite. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 567\u2013576 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298655","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"2891_CR134","doi-asserted-by":"publisher","unstructured":"Song, S., Xiao, J.: Sliding shapes for 3D object detection in depth images. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (Eds.), Computer Vision\u2014ECCV 2014, Springer International Publishing. pp. 634\u2013651 (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_41","DOI":"10.1007\/978-3-319-10599-4_41"},{"key":"2891_CR135","doi-asserted-by":"publisher","unstructured":"Song, S., Xiao, J.: Deep sliding shapes for amodal 3D object detection in RGB-D images. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 808\u2013816 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.94","DOI":"10.1109\/CVPR.2016.94"},{"key":"2891_CR136","doi-asserted-by":"publisher","unstructured":"Srivastava, S., Jurie, F., Sharma, G.: Learning 2D to 3D lifting for object detection in 3D for autonomous vehicles. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4504\u20134511 (2019). https:\/\/doi.org\/10.1109\/IROS40897.2019.8967624","DOI":"10.1109\/IROS40897.2019.8967624"},{"key":"2891_CR137","doi-asserted-by":"publisher","unstructured":"Sun, H., Meng, Z., Du, X., Ang, M.H.: A 3D convolutional neural network towards real-time amodal 3D object detection. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 8331\u20138338 (2018). https:\/\/doi.org\/10.1109\/IROS.2018.8593837","DOI":"10.1109\/IROS.2018.8593837"},{"key":"2891_CR138","doi-asserted-by":"publisher","unstructured":"Sun, P., Kretzschmar, H., Dotiwalla, X., Chouard, A., Patnaik, V., Tsui, P., Guo, J., Zhou, Y., Chai, Y., Caine, B., Vasudevan, V., Han, W., Ngiam, J., Zhao, H., Timofeev, A., Ettinger, S., Krivokon, M., Gao, A., Joshi, A., Zhang, Y., Shlens, J., Chen, Z., Anguelov, D.: Scalability in perception for autonomous driving: waymo open dataset. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2443\u20132451 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00252","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"2891_CR139","doi-asserted-by":"publisher","unstructured":"Tang, Y.S., Lee, G.H.: Transferable semi-supervised 3D object detection from RGB-D data. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1931\u20131940 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00202","DOI":"10.1109\/ICCV.2019.00202"},{"key":"2891_CR140","doi-asserted-by":"publisher","unstructured":"Teng, Z., Xiao, J.: Surface-based general 3D object detection and pose estimation. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 5473\u20135479 (2014). https:\/\/doi.org\/10.1109\/ICRA.2014.6907664","DOI":"10.1109\/ICRA.2014.6907664"},{"key":"2891_CR141","doi-asserted-by":"publisher","unstructured":"Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., Guibas, L.: KPConv: flexible and deformable convolution for point clouds. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE, Seoul, Korea (South). pp. 6410\u20136419 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00651","DOI":"10.1109\/ICCV.2019.00651"},{"key":"2891_CR142","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JRR Uijlings","year":"2013","unstructured":"Uijlings, J.R.R., van de Sande, K.E.A., Gevers, T., Smeulders, A.W.M.: Selective search for object recognition. Int. J. Comput. Vis. 104, 154\u2013171 (2013). https:\/\/doi.org\/10.1007\/s11263-013-0620-5","journal-title":"Int. J. Comput. Vis."},{"key":"2891_CR143","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"P Viola","year":"2004","unstructured":"Viola, P., Jones, M.J.: Robust real-time face detection. Int. J. Comput. Vis. 57, 137\u2013154 (2004). https:\/\/doi.org\/10.1023\/B:VISI.0000013087.49260.fb","journal-title":"Int. J. Comput. Vis."},{"key":"2891_CR144","doi-asserted-by":"publisher","unstructured":"Wang, D.Z., Posner, I.: Voting for voting in online point cloud object detection. In: Robotics: Science and Systems XI, Robotics: Science and Systems Foundation. pp. 1\u20139 (2015). https:\/\/doi.org\/10.15607\/RSS.2015.XI.035","DOI":"10.15607\/RSS.2015.XI.035"},{"key":"2891_CR145","unstructured":"Wang, G., Tian, B., Zhang, Y., Chen, L., Cao, D., Wu, J.: Multi-view adaptive fusion network for 3d object detection (2020). arXiv:2011.00652 [cs]"},{"key":"2891_CR146","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/s19040893","volume":"19","author":"L Wang","year":"2019","unstructured":"Wang, L., Li, R., Shi, H., Sun, J., Zhao, L., Seah, H.S., Quah, C.K., Tandianus, B.: Multi-channel convolutional neural network based 3D object detection for indoor robot environmental perception. Sensors 19, 1\u201314 (2019). https:\/\/doi.org\/10.3390\/s19040893","journal-title":"Sensors"},{"key":"2891_CR147","unstructured":"Wang, Y., Ye, J.: An overview of 3d object detection (2020). arXiv:2010.15614 [cs]"},{"key":"2891_CR148","doi-asserted-by":"publisher","unstructured":"Wang, Z., Jia, K.: Frustum ConvNet: sliding frustums to aggregate local point-wise features for Amodal. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1742\u20131749 (2019). https:\/\/doi.org\/10.1109\/IROS40897.2019.8968513","DOI":"10.1109\/IROS40897.2019.8968513"},{"key":"2891_CR149","doi-asserted-by":"publisher","unstructured":"Wang, Z., Zhan, W., Tomizuka, M.: fusing bird\u2019s eye view LIDAR point cloud and front view camera image for 3D object detection. In: 2018 IEEE Intelligent Vehicles Symposium (IV), pp. 1\u20136 (2018). https:\/\/doi.org\/10.1109\/IVS.2018.8500387","DOI":"10.1109\/IVS.2018.8500387"},{"key":"2891_CR150","doi-asserted-by":"publisher","unstructured":"Weng, X., Kitani, K.: monocular 3D object detection with pseudo-LiDAR point cloud. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 857\u2013866 (2019). https:\/\/doi.org\/10.1109\/ICCVW.2019.00114","DOI":"10.1109\/ICCVW.2019.00114"},{"key":"2891_CR151","doi-asserted-by":"publisher","unstructured":"Wu, P., Gu, L., Yan, X., Xie, H., Wang, F.L., Cheng, G., Wei, M.: PV-RCNN++: semantical point-voxel feature interaction for 3D object detection. Vis. Comput.(2022). https:\/\/doi.org\/10.1007\/s00371-022-02672-2","DOI":"10.1007\/s00371-022-02672-2"},{"key":"2891_CR152","doi-asserted-by":"publisher","unstructured":"Xu, B., Chen, Z.: multi-level fusion based 3D object detection from monocular images. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2345\u20132353 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00249","DOI":"10.1109\/CVPR.2018.00249"},{"key":"2891_CR153","doi-asserted-by":"publisher","unstructured":"Xu, D., Anguelov, D., Jain, A.: PointFusion: deep sensor fusion for 3D bounding box estimation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 244\u2013253 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00033","DOI":"10.1109\/CVPR.2018.00033"},{"key":"2891_CR154","doi-asserted-by":"publisher","unstructured":"Yamazaki, T., Sugimura, D., Hamamoto, T.: Discovering correspondence among image sets with projection view preservation for 3D object detection in point clouds. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3111\u20133115 (2018). https:\/\/doi.org\/10.1109\/ICASSP.2018.8461677","DOI":"10.1109\/ICASSP.2018.8461677"},{"key":"2891_CR155","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan, Y., Mao, Y., Li, B.: SECOND: sparsely embedded convolutional detection. Sensors 18, 1\u201317 (2018). https:\/\/doi.org\/10.3390\/s18103337","journal-title":"Sensors"},{"key":"2891_CR156","unstructured":"Yang, B., Liang, M., Urtasun, R.: HDNET: exploiting HD maps for 3D object detection. In: Proceedings of The 2nd Conference on Robot Learning, PMLR. pp. 146\u2013155 (2018a)"},{"key":"2891_CR157","doi-asserted-by":"publisher","unstructured":"Yang, B., Luo, W., Urtasun, R.: PIXOR: real-time 3D object detection from point clouds. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7652\u20137660 (2018b). https:\/\/doi.org\/10.1109\/CVPR.2018.00798","DOI":"10.1109\/CVPR.2018.00798"},{"key":"2891_CR158","doi-asserted-by":"publisher","unstructured":"Yang, Z., Sun, Y., Liu, S., Jia, J.: 3DSSD: point-based 3D single stage object detector. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Seattle, WA, USA. pp. 11037\u201311045 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01105","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"2891_CR159","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Shen, X., Jia, J.: IPOD: Intensive point-based object detector for point cloud (2018c). arXiv:1812.05276 [cs]","DOI":"10.1109\/ICCV.2019.00204"},{"key":"2891_CR160","doi-asserted-by":"publisher","unstructured":"Yang, Z., Sun, Y., Liu, S., Shen, X., Jia, J.: STD: sparse-to-dense 3D object detector for point cloud. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE. pp. 1951\u20131960 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00204","DOI":"10.1109\/ICCV.2019.00204"},{"key":"2891_CR161","doi-asserted-by":"publisher","unstructured":"Yoo, J.H., Kim, Y., Kim, J., Choi, J.W.: 3D-CVF: generating joint camera and LiDAR features using cross-view spatial feature fusion for 3D object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (Eds.), Computer Vision - ECCV 2020. Springer International Publishing, Cham. volume12372, pp. 720\u2013736 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58583-9_43","DOI":"10.1007\/978-3-030-58583-9_43"},{"key":"2891_CR162","doi-asserted-by":"publisher","first-page":"3434","DOI":"10.1109\/LRA.2018.2852843","volume":"3","author":"Y Zeng","year":"2018","unstructured":"Zeng, Y., Hu, Y., Liu, S., Ye, J., Han, Y., Li, X., Sun, N.: RT3D: real-time 3-D vehicle detection in LiDAR point cloud for autonomous driving. IEEE Robot. Auto. Lett. 3, 3434\u20133440 (2018). https:\/\/doi.org\/10.1109\/LRA.2018.2852843","journal-title":"IEEE Robot. Auto. Lett."},{"key":"2891_CR163","doi-asserted-by":"crossref","unstructured":"Zhang, H., Yang, D., Yurtsever, E., Redmill, K.A., \u00f6zg\u00fcner, U.: Faraway-frustum: Dealing with lidar sparsity for 3d object detection using fusion (2020). arXiv:2011.01404 [cs]","DOI":"10.1109\/ITSC48978.2021.9564990"},{"key":"2891_CR164","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","volume":"30","author":"ZQ Zhao","year":"2019","unstructured":"Zhao, Z.Q., Zheng, P., Xu, S.T., Wu, X.: Object detection with deep learning: a review. IEEE Trans. Neural Netw. Learn. Syst. 30, 3212\u20133232 (2019). https:\/\/doi.org\/10.1109\/TNNLS.2018.2876865","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"2891_CR165","doi-asserted-by":"crossref","unstructured":"Zheng, W., Tang, W., Chen, S., Jiang, L., Fu, C.W.: CIA-SSD: Confident IoU-aware single-stage object detector from point cloud (2020). arXiv:2012.03015 [cs]","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"2891_CR166","doi-asserted-by":"publisher","unstructured":"Zhong, Y., Wang, J., Peng, J., Zhang, L.: Anchor box optimization for object detection. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE, Snowmass Village, CO, USA. pp. 1275\u20131283 (2020). https:\/\/doi.org\/10.1109\/WACV45572.2020.9093498","DOI":"10.1109\/WACV45572.2020.9093498"},{"key":"2891_CR167","doi-asserted-by":"publisher","unstructured":"Zhou, D., Fang, J., Song, X., Liu, L., Yin, J., Dai, Y., Li, H., Yang, R.: Joint 3d instance segmentation and object detection for autonomous driving. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE. pp. 1836\u20131846 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00191","DOI":"10.1109\/CVPR42600.2020.00191"},{"key":"2891_CR168","doi-asserted-by":"publisher","unstructured":"Zhou, J., Tan, X., Shao, Z., Ma, L.: FVNet: 3D front-view proposal generation for real-time object detection from point clouds. In: 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), pp. 1\u20138 (2019). https:\/\/doi.org\/10.1109\/CISP-BMEI48845.2019.8965844","DOI":"10.1109\/CISP-BMEI48845.2019.8965844"},{"key":"2891_CR169","doi-asserted-by":"publisher","unstructured":"Zhou, Y., Tuzel, O.: VoxelNet: End-to-end learning for point cloud based 3D object detection. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4490\u20134499 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00472","DOI":"10.1109\/CVPR.2018.00472"},{"key":"2891_CR170","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1007\/s11263-014-0780-y","volume":"112","author":"MZ Zia","year":"2015","unstructured":"Zia, M.Z., Stark, M., Schindler, K.: Towards scene understanding with detailed 3D object representations. Int. J. Comput. Vis. 112, 188\u2013203 (2015). https:\/\/doi.org\/10.1007\/s11263-014-0780-y","journal-title":"Int. J. Comput. Vis."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02891-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-023-02891-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02891-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,18]],"date-time":"2024-02-18T23:17:16Z","timestamp":1708298236000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-023-02891-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,11]]},"references-count":170,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["2891"],"URL":"https:\/\/doi.org\/10.1007\/s00371-023-02891-1","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,11]]},"assertion":[{"value":"1 May 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 July 2023","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 competing interests to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}