{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T20:18:34Z","timestamp":1783714714191,"version":"3.55.0"},"reference-count":223,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134317","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:53:23Z","timestamp":1783061603000},"page":"134317","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Generalized deep-learning LiDAR-camera fusion method of 3D object detection for autonomous driving: A survey"],"prefix":"10.1016","volume":"699","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1030-0678","authenticated-orcid":false,"given":"Xianlu","family":"Tao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6517-2659","authenticated-orcid":false,"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuguo","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaoyang","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feixuan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"12","key":"10.1016\/j.neucom.2026.134317_bib0005","doi-asserted-by":"crossref","first-page":"3668","DOI":"10.3390\/s25123668","article-title":"A survey of deep learning-driven 3D object detection: sensor modalities, technical architectures, and applications","volume":"25","author":"Zhang","year":"2025","journal-title":"Sensors"},{"key":"10.1016\/j.neucom.2026.134317_bib0010","article-title":"A comprehensive survey on multi-sensor information processing and fusion for BEV perception in autonomous vehicles","author":"Ping","year":"2025","journal-title":"Inf. Fusion"},{"issue":"2","key":"10.1016\/j.neucom.2026.134317_bib0015","doi-asserted-by":"crossref","first-page":"722","DOI":"10.1109\/TITS.2020.3023541","article-title":"Deep learning for image and point cloud fusion in autonomous driving: a review","volume":"23","author":"Cui","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.neucom.2026.134317_bib0020","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4009","article-title":"Adabins: depth estimation using adaptive bins","author":"Bhat","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib0025","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10106","article-title":"Unidepth: universal monocular metric depth estimation","author":"Piccinelli","year":"2024"},{"key":"10.1016\/j.neucom.2026.134317_bib0030","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1907","article-title":"Multi-view 3D object detection network for autonomous driving","author":"Chen","year":"2017"},{"key":"10.1016\/j.neucom.2026.134317_bib0035","series-title":"2018 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"3194","article-title":"A general pipeline for 3D detection of vehicles","author":"Du","year":"2018"},{"key":"10.1016\/j.neucom.2026.134317_bib0040","author":"Liu"},{"key":"10.1016\/j.neucom.2026.134317_bib0045","first-page":"1","article-title":"A survey of collaborative perception in intelligent vehicles at intersections","author":"Gao","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.neucom.2026.134317_bib0050","first-page":"3125","article-title":"Collaborative sensing and communication for intelligent connected vehicles: a comprehensive survey","volume":"25","author":"Liu","year":"2025","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"10.1016\/j.neucom.2026.134317_bib0055","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/JPROC.2025.3608874","article-title":"Cooperative perception for automated driving: a survey of algorithms, applications, and future directions","author":"Wei","year":"2025","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.neucom.2026.134317_bib0060","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"284","article-title":"HM-ViT: hetero-modal vehicle-to-vehicle cooperative perception with vision transformer","author":"Xiang","year":"2023"},{"issue":"2","key":"10.1016\/j.neucom.2026.134317_bib0065","doi-asserted-by":"crossref","first-page":"2153","DOI":"10.1109\/TITS.2023.3314919","article-title":"V2VFormer++: multi-modal vehicle-to-vehicle cooperative perception via global-local transformer","volume":"25","author":"Yin","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"11","key":"10.1016\/j.neucom.2026.134317_bib0070","doi-asserted-by":"crossref","first-page":"16142","DOI":"10.1109\/JIOT.2025.3531145","article-title":"MDNet: multi-modal cooperative perception via spatial alignment of modal decision-making","volume":"12","author":"He","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.neucom.2026.134317_bib0075","series-title":"2022 5th World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM)","first-page":"811","article-title":"Multistage fusion approach of LiDAR and camera for vehicle-infrastructure cooperative object detection","author":"Yu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134317_bib0080","series-title":"2022 IEEE 13th International Symposium on Parallel Architectures, Algorithms and Programming (PAAP)","first-page":"1","article-title":"Multi-modal virtual-real fusion based transformer for collaborative perception","author":"Zhang","year":"2022"},{"issue":"3","key":"10.1016\/j.neucom.2026.134317_bib0085","doi-asserted-by":"crossref","first-page":"2043","DOI":"10.1109\/TMC.2024.3486758","article-title":"V2I-coop: accurate object detection for connected automated vehicles at accident black spots with v2I cross-modality cooperation","volume":"24","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Mob. Comput."},{"issue":"8","key":"10.1016\/j.neucom.2026.134317_bib0090","doi-asserted-by":"crossref","first-page":"1909","DOI":"10.1007\/s11263-023-01790-1","article-title":"3D object detection for autonomous driving: a comprehensive survey","volume":"131","author":"Mao","year":"2023","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.134317_bib0095","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126587","article-title":"Multi-modality 3D object detection in autonomous driving: a review","volume":"553","author":"Tang","year":"2023","journal-title":"Neurocomputing"},{"issue":"12","key":"10.1016\/j.neucom.2026.134317_bib0100","doi-asserted-by":"crossref","first-page":"21033","DOI":"10.1109\/JSEN.2025.3562284","article-title":"Developments in 3D object detection for autonomous driving: a review","volume":"25","author":"Wang","year":"2025","journal-title":"IEEE Sens. J."},{"key":"10.1016\/j.neucom.2026.134317_bib0105","first-page":"16494","article-title":"Multimodal virtual point 3D detection","volume":"34","author":"Yin","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134317_bib0110","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"918","article-title":"Frustum pointnets for 3D object detection from RGB-D data","author":"Qi","year":"2018"},{"key":"10.1016\/j.neucom.2026.134317_bib0115","series-title":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"1742","article-title":"Frustum convnet: sliding frustums to aggregate local point-wise features for amodal 3D object detection","author":"Wang","year":"2019"},{"key":"10.1016\/j.neucom.2026.134317_bib0120","series-title":"2019 IEEE Intelligent Vehicles Symposium (IV)","first-page":"2510","article-title":"Roarnet: a robust 3D object detection based on region approximation refinement","author":"Shin","year":"2019"},{"key":"10.1016\/j.neucom.2026.134317_bib0125","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.neucom.2021.08.155","article-title":"Deep learning-based perception systems for autonomous driving: a comprehensive survey","volume":"489","author":"Wen","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134317_bib0130","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126587","article-title":"Multi-modality 3D object detection in autonomous driving: a review","volume":"553","author":"Tang","year":"2023","journal-title":"Neurocomputing"},{"issue":"7","key":"10.1016\/j.neucom.2026.134317_bib0135","doi-asserted-by":"crossref","first-page":"3781","DOI":"10.1109\/TIV.2023.3264658","article-title":"Multi-modal 3D object detection in autonomous driving: a survey and taxonomy","volume":"8","author":"Wang","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.neucom.2026.134317_bib0140","series-title":"European Conference on Computer Vision","first-page":"194","article-title":"Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D","author":"Philion","year":"2020"},{"key":"10.1016\/j.neucom.2026.134317_bib0145","doi-asserted-by":"crossref","first-page":"18442","DOI":"10.52202\/068431-1340","article-title":"Unifying voxel-based representation with transformer for 3D object detection","volume":"35","author":"Li","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134317_bib0150","doi-asserted-by":"crossref","first-page":"10421","DOI":"10.52202\/068431-0757","article-title":"Bevfusion: a simple and robust LiDAR-camera fusion framework","volume":"35","author":"Liang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"10.1016\/j.neucom.2026.134317_bib0155","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1016\/j.icte.2021.12.016","article-title":"A sensor fusion system with thermal infrared camera and LiDAR for autonomous vehicles and deep learning based object detection","volume":"9","author":"Choi","year":"2023","journal-title":"ICT Express"},{"key":"10.1016\/j.neucom.2026.134317_bib0160","series-title":"2025 IEEE International Conference on Multimedia and Expo: Journey to the Center of Machine Imagination, ICME 2025-Conference Proceedings","article-title":"LFNet: cross-modal LiDAR-Fisheye fusion network for 3D semantic segmentation","author":"Zhang","year":"2025"},{"key":"10.1016\/j.neucom.2026.134317_bib0165","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"27197","article-title":"Ev-3dod: pushing the temporal boundaries of 3D object detection with event cameras","author":"Cho","year":"2025"},{"issue":"2","key":"10.1016\/j.neucom.2026.134317_bib0170","doi-asserted-by":"crossref","first-page":"1148","DOI":"10.1109\/TITS.2023.3317372","article-title":"Multi-sensor fusion technology for 3D object detection in autonomous driving: a review","volume":"25","author":"Wang","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.neucom.2026.134317_bib0175","series-title":"2024 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"9018","article-title":"Influence of camera-lidar configuration on 3D object detection for autonomous driving","author":"Li","year":"2024"},{"issue":"4","key":"10.1016\/j.neucom.2026.134317_bib0180","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1109\/MSP.2020.2973615","article-title":"LiDAR for autonomous driving: the principles, challenges, and trends for automotive LiDAR and perception systems","volume":"37","author":"Li","year":"2020","journal-title":"IEEE Signal Process. Mag."},{"key":"10.1016\/j.neucom.2026.134317_bib0185","series-title":"2020 16th International Conference on Intelligent Environments (IE)","first-page":"1","article-title":"Privacy-preserving people detection enabled by solid state LiDAR","author":"G\u00fcnter","year":"2020"},{"issue":"22","key":"10.1016\/j.neucom.2026.134317_bib0190","doi-asserted-by":"crossref","first-page":"25547","DOI":"10.1109\/JSEN.2021.3118952","article-title":"Modeling cameras for autonomous vehicle and robot simulation: an overview","volume":"21","author":"Elmquist","year":"2021","journal-title":"IEEE Sens. J."},{"key":"10.1016\/j.neucom.2026.134317_bib0195","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.105919","article-title":"RGB-T image analysis technology and application: a survey","volume":"120","author":"Song","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.134317_bib0200","series-title":"European Conference on Computer Vision","first-page":"342","article-title":"Recent event camera innovations: a survey","author":"Chakravarthi","year":"2024"},{"key":"10.1016\/j.neucom.2026.134317_bib0205","series-title":"2004 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)(IEEE Cat. No. 04CH37566), 3","first-page":"2301","article-title":"Extrinsic calibration of a camera and laser range finder (improves camera calibration)","author":"Zhang","year":"2004"},{"issue":"11","key":"10.1016\/j.neucom.2026.134317_bib0210","doi-asserted-by":"crossref","first-page":"15342","DOI":"10.1109\/TITS.2024.3419758","article-title":"Survey of extrinsic calibration on LiDAR-camera system for intelligent vehicle: challenges, approaches, and trends","volume":"25","author":"An","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"11","key":"10.1016\/j.neucom.2026.134317_bib0215","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"2002","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.neucom.2026.134317_bib0220","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134317_bib0225","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"779","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"10.1016\/j.neucom.2026.134317_bib0230","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"7263","article-title":"YOLO9000: better, faster, stronger","author":"Redmon","year":"2017"},{"key":"10.1016\/j.neucom.2026.134317_bib0235","author":"Redmon"},{"key":"10.1016\/j.neucom.2026.134317_bib0240","author":"Bochkovskiy"},{"key":"10.1016\/j.neucom.2026.134317_bib0245","series-title":"European Conference on Computer Vision","first-page":"21","article-title":"SSD: single shot multibox detector","author":"Liu","year":"2016"},{"key":"10.1016\/j.neucom.2026.134317_bib0250","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.neucom.2026.134317_bib0255","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2014"},{"key":"10.1016\/j.neucom.2026.134317_bib0260","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"1440","article-title":"Fast R-CNN","author":"Girshick","year":"2015"},{"issue":"6","key":"10.1016\/j.neucom.2026.134317_bib0265","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134317_bib0270","author":"Howard"},{"key":"10.1016\/j.neucom.2026.134317_bib0275","series-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops","article-title":"YOLO3D: end-to-end real-time 3D oriented object bounding box detection from LiDAR point cloud","author":"Ali","year":"2018"},{"key":"10.1016\/j.neucom.2026.134317_bib0280","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"7652","article-title":"Pixor: real-time 3D object detection from point clouds","author":"Yang","year":"2018"},{"key":"10.1016\/j.neucom.2026.134317_bib0285","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neucom.2026.134317_bib0290","author":"Dosovitskiy"},{"key":"10.1016\/j.neucom.2026.134317_bib0295","author":"Simonyan"},{"key":"10.1016\/j.neucom.2026.134317_bib0300","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2403","article-title":"Deep layer aggregation","author":"Yu","year":"2018"},{"key":"10.1016\/j.neucom.2026.134317_bib0305","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","article-title":"An energy and GPU-computation efficient backbone network for real-time object detection","author":"Lee","year":"2019"},{"key":"10.1016\/j.neucom.2026.134317_bib0310","author":"Chong"},{"key":"10.1016\/j.neucom.2026.134317_bib0315","first-page":"1","article-title":"UA-fusion: uncertainty-aware multimodal data fusion framework for 3D object detection of autonomous vehicles","volume":"74","author":"Shao","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.neucom.2026.134317_bib0320","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib0325","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"6792","article-title":"Unitr: a unified and efficient multi-modal transformer for bird\u2019s-eye-view representation","author":"Wang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134317_bib0330","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"568","article-title":"Pyramid vision transformer: a versatile backbone for dense prediction without convolutions","author":"Wang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib0335","author":"Chen"},{"key":"10.1016\/j.neucom.2026.134317_bib0340","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11976","article-title":"A convnet for the 2020s","author":"Liu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134317_bib0345","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2117","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.neucom.2026.134317_bib0350","series-title":"European Conference on Computer Vision","first-page":"354","article-title":"A unified multi-scale deep convolutional neural network for fast object detection","author":"Cai","year":"2016"},{"key":"10.1016\/j.neucom.2026.134317_bib0355","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10781","article-title":"Efficientdet: scalable and efficient object detection","author":"Tan","year":"2020"},{"key":"10.1016\/j.neucom.2026.134317_bib0360","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"8759","article-title":"Path aggregation network for instance segmentation","author":"Liu","year":"2018"},{"key":"10.1016\/j.neucom.2026.134317_bib0365","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"Chen","year":"2018"},{"key":"10.1016\/j.neucom.2026.134317_bib0370","author":"Cohen"},{"key":"10.1016\/j.neucom.2026.134317_bib0375","author":"Playout"},{"key":"10.1016\/j.neucom.2026.134317_bib0380","series-title":"Proceedings of the Winter Conference on Applications of Computer Vision","first-page":"944","article-title":"Continuous histogram for event-based vision camera systems","author":"Park","year":"2025"},{"key":"10.1016\/j.neucom.2026.134317_bib0385","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1731","article-title":"HATS: histograms of averaged time surfaces for robust event-based object classification","author":"Sironi","year":"2018"},{"key":"10.1016\/j.neucom.2026.134317_bib0390","author":"Sadoun"},{"key":"10.1016\/j.neucom.2026.134317_bib0395","author":"Ren"},{"key":"10.1016\/j.neucom.2026.134317_bib0400","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1172","article-title":"A voxel graph CNN for object classification with event cameras","author":"Deng","year":"2022"},{"key":"10.1016\/j.neucom.2026.134317_bib0405","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12677","article-title":"Lasernet: an efficient probabilistic 3D object detector for autonomous driving","author":"Meyer","year":"2019"},{"key":"10.1016\/j.neucom.2026.134317_bib0410","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"652","article-title":"Pointnet: deep learning on point sets for 3D classification and segmentation","author":"Qi","year":"2017"},{"key":"10.1016\/j.neucom.2026.134317_bib0415","article-title":"Pointnet++: deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134317_bib0420","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11040","article-title":"3DSSD: point-based 3D single stage object detector","author":"Yang","year":"2020"},{"key":"10.1016\/j.neucom.2026.134317_bib0425","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Pointrcnn: 3D object proposal generation and detection from point cloud","author":"Shi","year":"2019"},{"key":"10.1016\/j.neucom.2026.134317_bib0430","author":"Shi"},{"key":"10.1016\/j.neucom.2026.134317_bib0435","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"16259","article-title":"Point transformer","author":"Zhao","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib0440","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2906","article-title":"An end-to-end transformer model for 3D object detection","author":"Misra","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib0445","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4840","article-title":"Point transformer v3: simpler faster stronger","author":"Wu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134317_bib0450","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4490","article-title":"Voxelnet: end-to-end learning for point cloud based 3D object detection","author":"Zhou","year":"2018"},{"key":"10.1016\/j.neucom.2026.134317_bib0455","author":"Graham"},{"key":"10.1016\/j.neucom.2026.134317_bib0460","author":"Graham"},{"issue":"10","key":"10.1016\/j.neucom.2026.134317_bib0465","doi-asserted-by":"crossref","first-page":"3337","DOI":"10.3390\/s18103337","article-title":"Second: sparsely embedded convolutional detection","volume":"18","author":"Yan","year":"2018","journal-title":"Sensors"},{"key":"10.1016\/j.neucom.2026.134317_bib0470","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10529","article-title":"PV-RCNN: point-voxel feature set abstraction for 3D object detection","author":"Shi","year":"2020"},{"key":"10.1016\/j.neucom.2026.134317_bib0475","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 35","first-page":"1201","article-title":"Voxel R-CNN: towards high performance voxel-based 3D object detection","author":"Deng","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib0480","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3164","article-title":"Voxel transformer for 3D object detection","author":"Mao","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib0485","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21674","article-title":"Voxelnext: fully sparse voxelnet for 3D object detection and tracking","author":"Chen","year":"2023"},{"key":"10.1016\/j.neucom.2026.134317_bib0490","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14477","article-title":"Safdnet: a simple and effective network for fully sparse 3D object detection","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134317_bib0495","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12697","article-title":"Pointpillars: fast encoders for object detection from point clouds","author":"Lang","year":"2019"},{"key":"10.1016\/j.neucom.2026.134317_bib0500","series-title":"European Conference on Computer Vision","first-page":"35","article-title":"Pillarnet: real-time and high-performance pillar-based 3D object detection","author":"Shi","year":"2022"},{"key":"10.1016\/j.neucom.2026.134317_bib0505","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"17567","article-title":"PillarNeXt: rethinking network designs for 3D object detection in LiDAR point clouds","author":"Li","year":"2023"},{"key":"10.1016\/j.neucom.2026.134317_bib0510","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"27336","article-title":"Pillarhist: a quantization-aware pillar feature encoder based on height-aware histogram","author":"Zhou","year":"2025"},{"key":"10.1016\/j.neucom.2026.134317_bib0515","doi-asserted-by":"crossref","first-page":"53076","DOI":"10.52202\/075280-2309","article-title":"Hednet: a hierarchical encoder-decoder network for 3D object detection in point clouds","volume":"36","author":"Zhang","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134317_bib0520","series-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3354","article-title":"Are we ready for autonomous driving? The kitti vision benchmark suite","author":"Geiger","year":"2012"},{"key":"10.1016\/j.neucom.2026.134317_bib0525","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11621","article-title":"nuscenes: a multimodal dataset for autonomous driving","author":"Caesar","year":"2020"},{"key":"10.1016\/j.neucom.2026.134317_bib0530","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2446","article-title":"Scalability in perception for autonomous driving: waymo open dataset","author":"Sun","year":"2020"},{"key":"10.1016\/j.neucom.2026.134317_bib0535","series-title":"2020 IEEE Intelligent Vehicles Symposium (IV)","first-page":"1094","article-title":"LIBRE: the multiple 3D LiDAR dataset","author":"Carballo","year":"2020"},{"key":"10.1016\/j.neucom.2026.134317_bib0540","series-title":"2019 International Conference on Robotics and Automation (ICRA)","first-page":"9552","article-title":"The h3d dataset for full-surround 3D multi-object detection and tracking in crowded urban scenes","author":"Patil","year":"2019"},{"key":"10.1016\/j.neucom.2026.134317_bib0545","series-title":"2020 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"2267","article-title":"A* 3D dataset: towards autonomous driving in challenging environments","author":"Pham","year":"2020"},{"key":"10.1016\/j.neucom.2026.134317_bib0550","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9308","article-title":"Woodscape: a multi-task, multi-camera fisheye dataset for autonomous driving","author":"Yogamani","year":"2019"},{"key":"10.1016\/j.neucom.2026.134317_bib0555","series-title":"Conference on Robot Learning","first-page":"409","article-title":"One thousand and one hours: self-driving motion prediction dataset","author":"Houston","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib0560","series-title":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","first-page":"2987","article-title":"Pixset: an opportunity for 3D computer vision to go beyond point clouds with a full-waveform LiDAR dataset","author":"D\u00e9ziel","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib0565","author":"Mao"},{"key":"10.1016\/j.neucom.2026.134317_bib0570","series-title":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","first-page":"3095","article-title":"Pandaset: advanced sensor suite dataset for autonomous driving","author":"Xiao","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib0575","author":"Wilson"},{"key":"10.1016\/j.neucom.2026.134317_bib0580","author":"Zheng"},{"key":"10.1016\/j.neucom.2026.134317_bib0585","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"27446","article-title":"Robosense: large-scale dataset and benchmark for egocentric robot perception and navigation in crowded and unstructured environments","author":"Su","year":"2025"},{"key":"10.1016\/j.neucom.2026.134317_bib0590","doi-asserted-by":"crossref","first-page":"62062","DOI":"10.52202\/079017-1982","article-title":"Man truckscenes: a multimodal dataset for autonomous trucking in diverse conditions","volume":"37","author":"Fent","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134317_bib0595","series-title":"2022 International Conference on Robotics and Automation (ICRA)","first-page":"2539","article-title":"Ips300+: a challenging multi-modal data sets for intersection perception system","author":"Wang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134317_bib0600","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21361","article-title":"Dair-v2x: a large-scale dataset for vehicle-infrastructure cooperative 3D object detection","author":"Yu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134317_bib0605","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13712","article-title":"V2V4real: a real-world large-scale dataset for vehicle-to-vehicle cooperative perception","author":"Xu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134317_bib0610","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5486","article-title":"V2X-seq: a large-scale sequential dataset for vehicle-infrastructure cooperative perception and forecasting","author":"Yu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134317_bib0615","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"22668","article-title":"Tumtraf V2X cooperative perception dataset","author":"Zimmer","year":"2024"},{"key":"10.1016\/j.neucom.2026.134317_bib0620","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"22347","article-title":"Rcooper: a real-world large-scale dataset for roadside cooperative perception","author":"Hao","year":"2024"},{"key":"10.1016\/j.neucom.2026.134317_bib0625","series-title":"European Conference on Computer Vision","first-page":"455","article-title":"V2X-real: a largs-scale dataset for vehicle-to-everything cooperative perception","author":"Xiang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134317_bib0630","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"22129","article-title":"HoloVIC: large-scale dataset and benchmark for multi-sensor holographic intersection and vehicle-infrastructure cooperative","author":"Ma","year":"2024"},{"key":"10.1016\/j.neucom.2026.134317_bib0635","author":"Yang"},{"key":"10.1016\/j.neucom.2026.134317_bib0640","author":"Hou"},{"key":"10.1016\/j.neucom.2026.134317_bib0645","author":"Sekaran"},{"key":"10.1016\/j.neucom.2026.134317_bib0650","author":"Wang"},{"key":"10.1016\/j.neucom.2026.134317_bib0655","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","article-title":"Complexer-yolo: real-time 3D object detection and tracking on semantic point clouds","author":"Simon","year":"2019"},{"key":"10.1016\/j.neucom.2026.134317_bib0660","series-title":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","first-page":"3047","article-title":"Fusionpainting: multimodal fusion with adaptive attention for 3D object detection","author":"Xu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib0665","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 34","first-page":"12460","article-title":"PI-RCNN: an efficient multi-sensor 3D object detector with point-based attentive cont-conv fusion module","author":"Xie","year":"2020"},{"key":"10.1016\/j.neucom.2026.134317_bib0670","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21653","article-title":"Virtual sparse convolution for multimodal 3D object detection","author":"Wu","year":"2023"},{"issue":"9","key":"10.1016\/j.neucom.2026.134317_bib0675","doi-asserted-by":"crossref","first-page":"13618","DOI":"10.1109\/TVT.2025.3566696","article-title":"MUFFIN-HGCN: multi-feature fusion Hierarchical-GCN for 3D object detection","volume":"7","author":"Liu","year":"2025","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.neucom.2026.134317_bib0680","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"17524","article-title":"Logonet: towards accurate 3D object detection with local-to-global cross-modal fusion","author":"Li","year":"2023"},{"issue":"1","key":"10.1016\/j.neucom.2026.134317_bib0685","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1109\/TPAMI.2025.3609348","article-title":"Mv2dfusion: leveraging modality-specific object semantics for multi-modal 3D detection","volume":"48","author":"Wang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134317_bib0690","author":"Yang"},{"key":"10.1016\/j.neucom.2026.134317_bib0695","series-title":"2019 International Conference on Robotics and Automation (ICRA)","first-page":"7276","article-title":"Mvx-net: multimodal voxelnet for 3D object detection","author":"Sindagi","year":"2019"},{"key":"10.1016\/j.neucom.2026.134317_bib0700","series-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops","article-title":"Complex-yolo: an Euler-region-proposal for real-time 3D object detection on point clouds","author":"Simony","year":"2018"},{"key":"10.1016\/j.neucom.2026.134317_bib0705","author":"Paszke"},{"key":"10.1016\/j.neucom.2026.134317_bib0710","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4604","article-title":"Pointpainting: sequential fusion for 3D object detection","author":"Vora","year":"2020"},{"issue":"10","key":"10.1016\/j.neucom.2026.134317_bib0715","doi-asserted-by":"crossref","first-page":"18040","DOI":"10.1109\/TITS.2022.3154537","article-title":"CL3D: Camera-LiDAR 3D object detection with point feature enhancement and point-guided fusion","volume":"23","author":"Lin","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.neucom.2026.134317_bib0720","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5418","article-title":"Sparse fuse dense: towards high quality 3D detection with depth completion","author":"Wu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134317_bib0725","series-title":"2021 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"13656","article-title":"Penet: towards precise and efficient image guided depth completion","author":"Hu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib0730","first-page":"1","article-title":"Multi-sem fusion: multimodal semantic fusion for 3-D object detection","volume":"62","author":"Xu","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.134317_bib0735","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11784","article-title":"Center-based 3D object detection and tracking","author":"Yin","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib0740","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4974","article-title":"Hybrid task cascade for instance segmentation","author":"Chen","year":"2019"},{"key":"10.1016\/j.neucom.2026.134317_bib0745","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"11844","article-title":"ViKIENet: towards efficient 3D object detection with virtual key instance enhanced network","author":"Yu","year":"2025"},{"key":"10.1016\/j.neucom.2026.134317_bib0750","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.134317_bib0755","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"22266","article-title":"MonoTAKD: teaching assistant knowledge distillation for monocular 3D object detection","author":"Liu","year":"2025"},{"key":"10.1016\/j.neucom.2026.134317_bib0760","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"641","article-title":"Deep continuous fusion for multi-sensor 3D object detection","author":"Liang","year":"2018"},{"key":"10.1016\/j.neucom.2026.134317_bib0765","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"244","article-title":"Pointfusion: deep sensor fusion for 3D bounding box estimation","author":"Xu","year":"2018"},{"issue":"6","key":"10.1016\/j.neucom.2026.134317_bib0770","doi-asserted-by":"crossref","first-page":"5598","DOI":"10.1109\/TITS.2023.3347078","article-title":"PPF-det: point-pixel fusion for multi-modal 3D object detection","volume":"25","author":"Xie","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.neucom.2026.134317_bib0775","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"908","article-title":"Cat-det: contrastively augmented transformer for multi-modal 3D object detection","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134317_bib0780","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"8","key":"10.1016\/j.neucom.2026.134317_bib0785","doi-asserted-by":"crossref","first-page":"9397","DOI":"10.1109\/TITS.2024.3387398","article-title":"MENet: multi-modal mapping enhancement network for 3D object detection in autonomous driving","volume":"25","author":"Liu","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.neucom.2026.134317_bib0790","series-title":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"1","article-title":"Joint 3D proposal generation and object detection from view aggregation","author":"Ku","year":"2018"},{"key":"10.1016\/j.neucom.2026.134317_bib0795","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7345","article-title":"Multi-task multi-sensor fusion for 3D object detection","author":"Liang","year":"2019"},{"key":"10.1016\/j.neucom.2026.134317_bib0800","series-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"10386","article-title":"CLOCs: Camera-LiDAR object candidates fusion for 3D object detection","author":"Pang","year":"2020"},{"key":"10.1016\/j.neucom.2026.134317_bib0805","series-title":"European Conference on Computer Vision","first-page":"720","article-title":"3D-cvf: generating joint camera and LiDAR features using cross-view spatial feature fusion for 3D object detection","author":"Yoo","year":"2020"},{"key":"10.1016\/j.neucom.2026.134317_bib0810","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"3772","article-title":"Cross-modality 3D object detection","author":"Zhu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib0815","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"187","article-title":"Fast-CLOCs: fast camera-LiDAR object candidates fusion for 3D object detection","author":"Pang","year":"2022"},{"issue":"5","key":"10.1016\/j.neucom.2026.134317_bib0820","doi-asserted-by":"crossref","first-page":"3442","DOI":"10.1109\/TIV.2024.3454085","article-title":"Contrastive late fusion for 3D object detection","volume":"10","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.neucom.2026.134317_bib0825","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11794","article-title":"Pointaugmenting: cross-modal augmentation for 3D object detection","author":"Wang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib0830","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"6569","article-title":"Centernet: keypoint triplets for object detection","author":"Duan","year":"2019"},{"key":"10.1016\/j.neucom.2026.134317_bib0835","series-title":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","first-page":"3047","article-title":"Fusionpainting: multimodal fusion with adaptive attention for 3D object detection","author":"Xu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib0840","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 37","first-page":"1477","article-title":"Bevdepth: acquisition of reliable depth for multi-view 3D object detection","author":"Li","year":"2023"},{"key":"10.1016\/j.neucom.2026.134317_bib0845","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13343","article-title":"X3kd: knowledge distillation across modalities, tasks and stages for multi-camera 3D object detection","author":"Klingner","year":"2023"},{"key":"10.1016\/j.neucom.2026.134317_bib0850","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"8637","article-title":"Distillbev: boosting multi-camera 3D object detection with cross-modal knowledge distillation","author":"Wang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134317_bib0855","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5116","article-title":"Unidistill: a universal cross-modality knowledge distillation framework for 3D object detection in bird\u2019s-eye view","author":"Zhou","year":"2023"},{"issue":"1","key":"10.1016\/j.neucom.2026.134317_bib0860","doi-asserted-by":"crossref","first-page":"2489","DOI":"10.1109\/TIV.2023.3319430","article-title":"BEV-lgkd: a unified LiDAR-guided knowledge distillation framework for multi-view BEV 3D object detection","volume":"9","author":"Li","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.neucom.2026.134317_bib0865","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"20113","article-title":"Bevnext: reviving dense BEV frameworks for 3D object detection","author":"Li","year":"2024"},{"issue":"11","key":"10.1016\/j.neucom.2026.134317_bib0870","doi-asserted-by":"crossref","first-page":"21257","DOI":"10.1109\/TITS.2025.3599015","article-title":"HybridBEV: hybrid encode and distillation for improved BEV 3D object detection","volume":"26","author":"Wang","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.neucom.2026.134317_bib0875","author":"K\u00e4ppeler"},{"key":"10.1016\/j.neucom.2026.134317_bib0880","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13520","article-title":"Dsvt: dynamic sparse voxel transformer with rotated sets","author":"Wang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134317_bib0885","series-title":"European Conference on Computer Vision","first-page":"439","article-title":"Detecting as labeling: rethinking LiDAR-camera fusion in 3D object detection","author":"Huang","year":"2024"},{"issue":"7","key":"10.1016\/j.neucom.2026.134317_bib0890","doi-asserted-by":"crossref","first-page":"5753","DOI":"10.1109\/TCSVT.2024.3366664","article-title":"Toward robust LiDAR-camera fusion in BEV space via mutual deformable attention and temporal aggregation","volume":"34","author":"Wang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134317_bib0895","series-title":"European Conference on Computer Vision","first-page":"232","article-title":"Diffusion model for robust multi-sensor fusion in 3D object detection and BEV segmentation","author":"Le","year":"2024"},{"key":"10.1016\/j.neucom.2026.134317_bib0900","series-title":"2025 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"6291","article-title":"Explore the LiDAR-Camera dynamic adjustment fusion for 3D object detection","author":"Yang","year":"2025"},{"issue":"1","key":"10.1016\/j.neucom.2026.134317_bib0905","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1109\/TPAMI.2025.3612958","article-title":"MGAF: LiDAR-Camera 3D object detection with multiple guidance and adaptive fusion","volume":"48","author":"Fan","year":"2026","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134317_bib0910","series-title":"2025 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"8581","article-title":"Flatfusion: delving into details of sparse transformer-based camera-lidar fusion for autonomous driving","author":"Zhu","year":"2025"},{"key":"10.1016\/j.neucom.2026.134317_bib0915","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 40","first-page":"12448","article-title":"BEVDilation: LiDAR-Centric multi-modal fusion for 3D object detection","author":"Zhang","year":"2026"},{"key":"10.1016\/j.neucom.2026.134317_bib0920","doi-asserted-by":"crossref","first-page":"1992","DOI":"10.52202\/068431-0145","article-title":"Deepinteraction: 3D object detection via modality interaction","volume":"35","author":"Yang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134317_bib0925","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1090","article-title":"Transfusion: robust LiDAR-camera fusion for 3D object detection with transformers","author":"Bai","year":"2022"},{"issue":"5","key":"10.1016\/j.neucom.2026.134317_bib0930","doi-asserted-by":"crossref","first-page":"6027","DOI":"10.1109\/TITS.2026.3651273","article-title":"CrossRay3D: geometry and distribution guidance for efficient multimodal 3D detection","volume":"27","author":"Yang","year":"2026","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.neucom.2026.134317_bib0935","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"17591","article-title":"Sparsefusion: fusing multi-modal sparse representations for multi-sensor 3D object detection","author":"Xie","year":"2023"},{"key":"10.1016\/j.neucom.2026.134317_bib0940","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21643","article-title":"Msmdfusion: fusing LiDAR and camera at multiple scales with multi-depth seeds for 3D object detection","author":"Jiao","year":"2023"},{"issue":"12","key":"10.1016\/j.neucom.2026.134317_bib0945","doi-asserted-by":"crossref","first-page":"19917","DOI":"10.1109\/TITS.2024.3453963","article-title":"Multi-modal 3D object detection by box matching","volume":"25","author":"Liu","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"2","key":"10.1016\/j.neucom.2026.134317_bib0950","doi-asserted-by":"crossref","first-page":"1279","DOI":"10.1109\/TPAMI.2024.3502456","article-title":"Fsd v2: improving fully sparse 3D object detection with virtual voxels","volume":"47","author":"Fan","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134317_bib0955","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"17182","article-title":"Deepfusion: LiDAR-camera deep fusion for multi-modal 3D object detection","author":"Li","year":"2022"},{"key":"10.1016\/j.neucom.2026.134317_bib0960","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2926","article-title":"Frustum-pointpillars: a multi-stage approach for 3D object detection using RGB camera and LiDAR","author":"Paigwar","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib0965","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 33","first-page":"9267","article-title":"3D object detection using scale invariant and feature reweighting networks","author":"Zhao","year":"2019"},{"key":"10.1016\/j.neucom.2026.134317_bib0970","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2791","article-title":"Diversity matters: fully exploiting depth clues for reliable monocular 3D object detection","author":"Li","year":"2022"},{"key":"10.1016\/j.neucom.2026.134317_bib0975","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3793","article-title":"Monoground: detecting monocular 3D objects from the ground","author":"Qin","year":"2022"},{"key":"10.1016\/j.neucom.2026.134317_bib0980","series-title":"European Conference on Computer Vision","first-page":"311","article-title":"Rethinking pseudo-lidar representation","author":"Ma","year":"2020"},{"issue":"11","key":"10.1016\/j.neucom.2026.134317_bib0985","doi-asserted-by":"crossref","first-page":"17587","DOI":"10.1109\/TITS.2024.3412759","article-title":"MonoGAE: roadside monocular 3D object detection with ground-aware embeddings","volume":"25","author":"Yang","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.neucom.2026.134317_bib0990","author":"Hinton"},{"key":"10.1016\/j.neucom.2026.134317_bib0995","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7842","article-title":"General instance distillation for object detection","author":"Dai","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib1000","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8479","article-title":"Point-to-voxel knowledge distillation for LiDAR semantic segmentation","author":"Hou","year":"2022"},{"key":"10.1016\/j.neucom.2026.134317_bib1005","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11933","article-title":"Knowledge distillation with the reused teacher classifier","author":"Chen","year":"2022"},{"key":"10.1016\/j.neucom.2026.134317_bib1010","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"1365","article-title":"Similarity-preserving knowledge distillation","author":"Tung","year":"2019"},{"key":"10.1016\/j.neucom.2026.134317_bib1015","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11868","article-title":"Class attention transfer based knowledge distillation","author":"Guo","year":"2023"},{"key":"10.1016\/j.neucom.2026.134317_bib1020","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"18268","article-title":"Cross modal transformer: towards fast and robust 3D object detection","author":"Yan","year":"2023"},{"key":"10.1016\/j.neucom.2026.134317_bib1025","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8555","article-title":"Categorical depth distribution network for monocular 3D object detection","author":"Reading","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib1030","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8445","article-title":"Pseudo-lidar from visual depth estimation: bridging the gap in 3D object detection for autonomous driving","author":"Wang","year":"2019"},{"key":"10.1016\/j.neucom.2026.134317_bib1035","author":"Xie"},{"issue":"1","key":"10.1016\/j.neucom.2026.134317_bib1040","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1109\/TIV.2024.3409308","article-title":"PolarGFusion3D: polar graph fusion network for enhanced multimodal 3D perception in intelligent vehicles","volume":"10","author":"Li","year":"2025","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.neucom.2026.134317_bib1045","series-title":"2025 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"15733","article-title":"RoBiFusion: a robust and bidirectional interaction Camera-LiDAR 3D object detection framework","author":"Wen","year":"2025"},{"key":"10.1016\/j.neucom.2026.134317_bib1050","article-title":"Offset-corrected query generation strategies for cross-modality misalignment in 3D object detection: aligning LiDAR and camera","author":"Li","year":"2026","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134317_bib1055","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"357","article-title":"Crossvit: cross-attention multi-scale vision transformer for image classification","author":"Chen","year":"2021"},{"key":"10.1016\/j.neucom.2026.134317_bib1060","series-title":"2024 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"6600","article-title":"Lssattn: towards dense and accurate view transformation for multi-modal 3D object detection","author":"Jiang","year":"2024"},{"issue":"4","key":"10.1016\/j.neucom.2026.134317_bib1065","doi-asserted-by":"crossref","first-page":"4956","DOI":"10.1109\/TCSVT.2025.3628019","article-title":"DGFusion: dual-guided fusion for robust multi-modal 3D object detection","volume":"36","author":"Jia","year":"2026","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134317_bib1070","series-title":"2023 IEEE Conference on Artificial Intelligence (CAI)","first-page":"71","article-title":"Fast all-day 3D object detection based on multi-sensor fusion","author":"Xiao","year":"2023"},{"issue":"11","key":"10.1016\/j.neucom.2026.134317_bib1075","doi-asserted-by":"crossref","first-page":"5042","DOI":"10.1109\/TIV.2024.3511923","article-title":"VIL-PPGen: a novel pseudo point generator based on visible light camera, infrared camera and LiDAR","volume":"10","author":"Ai","year":"2025","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.neucom.2026.134317_bib1080","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21611","article-title":"Bevheight: a robust framework for vision-based roadside 3D object detection","author":"Yang","year":"2023"},{"issue":"6","key":"10.1016\/j.neucom.2026.134317_bib1085","doi-asserted-by":"crossref","first-page":"5094","DOI":"10.1109\/TPAMI.2025.3549711","article-title":"BEVHeight++: toward robust visual centric 3D object detection","volume":"47","author":"Yang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134317_bib1090","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 40","first-page":"9548","article-title":"Towards accurate 3D object detection in adverse weather by leveraging 4D radar for LiDAR geometry enhancement","author":"Tong","year":"2026"},{"key":"10.1016\/j.neucom.2026.134317_bib1095","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 40","first-page":"9948","article-title":"Temporal and spatial representation learning for multimodal low-beam 3D object detection","author":"Wang","year":"2026"},{"issue":"6","key":"10.1016\/j.neucom.2026.134317_bib1100","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1007\/s11633-025-1558-0","article-title":"A survey on end-to-end perception and prediction for autonomous driving","volume":"22","author":"Hu","year":"2025","journal-title":"Mach. Intell. Res."},{"key":"10.1016\/j.neucom.2026.134317_bib1105","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 40","first-page":"13226","article-title":"Multi-modal assistance for unsupervised domain adaptation on point cloud 3D object detection","author":"Zhao","year":"2026"},{"key":"10.1016\/j.neucom.2026.134317_bib1110","author":"Mumcu"},{"issue":"11","key":"10.1016\/j.neucom.2026.134317_bib1115","doi-asserted-by":"crossref","first-page":"12189","DOI":"10.1109\/LRA.2025.3619807","article-title":"Driveagent: multi-agent structured reasoning with LLM and multimodal sensor fusion for autonomous driving","volume":"10","author":"Hou","year":"2025","journal-title":"IEEE Robot. Autom. Lett."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226017157?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226017157?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T19:50:14Z","timestamp":1783713014000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226017157"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":223,"alternative-id":["S0925231226017157"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134317","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Generalized deep-learning LiDAR-camera fusion method of 3D object detection for autonomous driving: A survey","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134317","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"134317"}}