{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:07:21Z","timestamp":1788934041831,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":97,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372314","type":"print"},{"value":"9783032372321","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37232-1_9","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:51:33Z","timestamp":1788933093000},"page":"152-171","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LeAD-M3D: Leveraging Asymmetric Distillation for\u00a0Real-Time Monocular 3D Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2227-8271","authenticated-orcid":false,"given":"Johannes","family":"Meier","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2314-8283","authenticated-orcid":false,"given":"Jonathan","family":"Michel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6842-5220","authenticated-orcid":false,"given":"Oussema","family":"Dhaouadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0044-515X","authenticated-orcid":false,"given":"Yung-Hsu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8616-1627","authenticated-orcid":false,"given":"Christoph","family":"Reich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8447-2344","authenticated-orcid":false,"given":"Zuria","family":"Bauer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9002-9832","authenticated-orcid":false,"given":"Stefan","family":"Roth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2448-2318","authenticated-orcid":false,"given":"Marc","family":"Pollefeys","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7487-6185","authenticated-orcid":false,"given":"Jacques","family":"Kaiser","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3079-7984","authenticated-orcid":false,"given":"Daniel","family":"Cremers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"issue":"9","key":"9_CR1","doi-asserted-by":"publisher","first-page":"4679","DOI":"10.1007\/s00170-025-16548-x","volume":"140","author":"T Boroukhian","year":"2025","unstructured":"Boroukhian, T., Supyen, K., Samson, J.B., Bashyal, A., Wicaksono, H.: Integrating 3D object detection with ontologies for accurate digital twin creation in manufacturing systems. Int. J. Adv. Manuf. Technol. 140(9), 4679\u20134711 (2025)","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Brazil, G., Kumar, A., Straub, J., Ravi, N., Johnson, J., Gkioxari, G.: Omni3D: a large benchmark and model for 3D object detection in the wild. In: CVPR, pp. 13154\u201313164 (2023)","DOI":"10.1109\/CVPR52729.2023.01264"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Brazil, G., Liu, X.: M3D-RPN: monocular 3D region proposal network for object detection. In: ICCV, pp. 9286\u20139295 (2019)","DOI":"10.1109\/ICCV.2019.00938"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Brazil, G., Pons-Moll, G., Liu, X., Schiele, B.: Kinematic 3D object detection in monocular video. In: ECCV, Vol. 12368, pp. 135\u2013152 (2020)","DOI":"10.1007\/978-3-030-58592-1_9"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: NUsCENES: a multimodal dataset for autonomous driving, pp. 11618\u201311628. CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"9_CR6","unstructured":"Chen, G., Choi, W., Yu, X., Han, T.X., Chandraker, M.: Learning efficient object detection models with knowledge distillation. In: NeurIPS, vol. 30, pp 742\u2013751 (2017)"},{"issue":"12","key":"9_CR7","doi-asserted-by":"publisher","first-page":"10164","DOI":"10.1109\/TPAMI.2024.3435937","volume":"46","author":"L Chen","year":"2024","unstructured":"Chen, L., Wu, P., Chitta, K., Jaeger, B., Geiger, A., Li, H.: End-to-end autonomous driving: challenges and frontiers. IEEE Trans. Pattern Anal. Mach. Intell. 46(12), 10164\u201310183 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR8","unstructured":"Chen, Q., et al.: LW-DETR: a transformer replacement to YOLO for real-time detection. arXiv:2406.03459 (2024)"},{"key":"9_CR9","unstructured":"Chen, X., Chen, M., Tang, S., Niu, Y., Zhu, J.: MOSE: boosting vision-based roadside 3D object detection with scene cues. arXiv:2404.05280 (2024)"},{"key":"9_CR10","unstructured":"Chen, X., et al.: 3D object proposals for accurate object class detection. NIPS 28 (2015)"},{"key":"9_CR11","doi-asserted-by":"publisher","first-page":"2665","DOI":"10.1109\/TIP.2024.3378475","volume":"33","author":"H Cheng","year":"2024","unstructured":"Cheng, H., Peng, L., Yang, Z., Lin, B., He, X., Wu, B.: Temporal feature fusion for 3D detection in monocular video. IEEE Trans. Image Process. 33, 2665\u20132675 (2024)","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"9_CR12","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1109\/TIV.2023.3318070","volume":"9","author":"PS Chib","year":"2024","unstructured":"Chib, P.S., Singh, P.: Recent advancements in end-to-end autonomous driving using deep learning: A survey. IEEE Trans. Intell. Veh. 9(1), 103\u2013118 (2024)","journal-title":"IEEE Trans. Intell. Veh."},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Choi, W., Shin, M., Im, S.: Depth-discriminative metric learning for monocular 3D object detection. NeurIPS, vol 36, 80165\u201380177 (2023)","DOI":"10.52202\/075280-3512"},{"key":"9_CR14","unstructured":"Chong, Z., et al.: MonoDistill: learning spatial features for monocular 3D object detection, p. ICLR (2022)"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.: RandAugment: Practical automated data augmentation with a reduced search space. In: NeurIPS, vol. 33, pp. 18613\u201318624 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Dhaouadi, O., et al.: Highly accurate and diverse traffic data: the deepscenario open 3D dataset. In: IV, pp. 377\u2013384 (2025)","DOI":"10.1109\/IV64158.2025.11097484"},{"issue":"10","key":"9_CR17","doi-asserted-by":"publisher","first-page":"9925","DOI":"10.1109\/TCSVT.2024.3405992","volume":"34","author":"R Ding","year":"2024","unstructured":"Ding, R., Yang, M., Zheng, N.: Selective transfer learning of cross-modality distillation for monocular 3D object detection. IEEE Trans. Circuits Syst. Video Technol. 34(10), 9925\u20139938 (2024)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"9_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112418","volume":"172","author":"J Dong","year":"2026","unstructured":"Dong, J., et al.: MonoA2: adaptive depth with augmented head for monocular 3D object detection. Pattern Recognit. 172, 112418 (2026)","journal-title":"Pattern Recognit."},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Fan, Z., et al.: MonoSG: monocular 3D object detection with stereo guidance. IEEE Robotics Autom. Lett. 10(4), 3604\u20133611 (2025)","DOI":"10.1109\/LRA.2025.3544487"},{"key":"9_CR20","unstructured":"Fischer, T., Yang, Y.H., Kumar, S., Sun, M., Yu, F.: CC-3DT: panoramic 3D object tracking via cross-camera fusion. CoRL (2022)"},{"key":"9_CR21","volume-title":"MonoFG: monocular 3D object detection with knowledge distillation for human-centric autonomous driving systems","author":"H Gao","year":"2024","unstructured":"Gao, H., Yu, X., Xu, Y., Ran, Q., Hussain, W.: MonoFG: monocular 3D object detection with knowledge distillation for human-centric autonomous driving systems. ACM Trans. Auton. Adapt, Syst (2024)"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the KITTI vision benchmark suite. In: CVPR, pp. 3354\u20133361 (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"issue":"6","key":"9_CR23","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2021","unstructured":"Gou, J., Yu, B., Maybank, S.J., Tao, D.: Knowledge distillation: a survey. Int. J. Comput. Vis. 129(6), 1789\u20131819 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"issue":"1","key":"9_CR25","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1109\/TIV.2023.3311949","volume":"9","author":"X He","year":"2024","unstructured":"He, X., et al.: SSD-MonoDETR: supervised scale-aware deformable transformer for monocular 3D object detection. IEEE Trans. Intell. Veh. 9(1), 555\u2013567 (2024)","journal-title":"IEEE Trans. Intell. Veh."},{"key":"9_CR26","unstructured":"Hinton, G.E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Deep Learning and Representation Learning Workshop (2014)"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Hong, Y., Dai, H., Ding, Y.: Cross-modality knowledge distillation network for monocular 3D object detection. In: ECCV. vol. 13670, pp. 87\u2013104 (2022)","DOI":"10.1007\/978-3-031-20080-9_6"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Hu, H.N., et al.: Joint monocular 3D vehicle detection and tracking. In: ICCV, pp. 5390\u20135399 (2019)","DOI":"10.1109\/ICCV.2019.00549"},{"key":"9_CR29","unstructured":"Im, E., Lee, J.K., Jee, C.: GATE3D: generalized attention-based task-synergized estimation in 3D, CVPRW (2025)"},{"issue":"11","key":"9_CR30","doi-asserted-by":"publisher","first-page":"16312","DOI":"10.1109\/TITS.2024.3411159","volume":"25","author":"Y Ji","year":"2024","unstructured":"Ji, Y., Xu, J.: Depth estimation from surface-ground correspondence for monocular 3D object detection. IEEE Trans. Intell. Transp. Syst. 25(11), 16312\u201316322 (2024)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Jia, J., Li, Z., Shi, Y.: MonoUNI: A unified vehicle and infrastructure-side monocular 3D object detection network with sufficient depth clues. In: NeurIPS, vol. 36, pp. 11703\u201311715 (2023)","DOI":"10.52202\/075280-0514"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Jiang, X., Jin, S., Zhang, X., Shao, L., Lu, S.: MonoMAE: enhancing monocular 3D detection through depth-aware masked autoencoders. In: NeurIPS, vol. 37,pp. 11392\u201311411 (2024)","DOI":"10.52202\/079017-0362"},{"key":"9_CR33","doi-asserted-by":"publisher","first-page":"2749","DOI":"10.1109\/TIP.2023.3274479","volume":"32","author":"JU Kim","year":"2023","unstructured":"Kim, J.U., Kim, H., Ro, Y.M.: Stereoscopic vision recalling memory for monocular 3D object detection. IEEE Trans. Image Process. 32, 2749\u20132760 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"9_CR34","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization, p. ICLR (2015)"},{"key":"9_CR35","unstructured":"Kotthapalli, M., Ravipati, D., Bhatia, R.: YOLOv1 to YOLOv11: a comprehensive survey of real-time object detection innovations and challenges. arXiv:2508.02067 [cs.CV] (2025)"},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Kumar, A., Brazil, G., Corona, E., Parchami, A., Liu, X.: DEVIANT: depth equivariant network for monocular 3D object detection. In: ECCV, vol. 13669,pp. 664\u2013683 (2022)","DOI":"10.1007\/978-3-031-20077-9_39"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Le, D.T., Pham, T., Cai, J., Rezatofighi, H.: Marginalized generalized IoU (MGIoU): a unified objective function for optimizing any convex parametric shapes. arXiv:2504.16443 (2025)","DOI":"10.1609\/aaai.v40i7.37505"},{"key":"9_CR38","unstructured":"Lei, M., et al.: YOLOv13: real-time object detection with hypergraph-enhanced adaptive visual perception. arXiv:2506.17733 (2025)"},{"key":"9_CR39","doi-asserted-by":"crossref","unstructured":"Li, M., Ma, N.: Overview of 3D object detection for robot environment perception. ICIVIS, pp. 675\u2013681 (2023)","DOI":"10.1007\/978-981-97-0855-0_64"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, Y., He, J., Zhang, Z.: Densely constrained depth estimator for monocular 3D object detection. In: ECCV, vol. 13669,pp. 718\u2013734 (2022)","DOI":"10.1007\/978-3-031-20077-9_42"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: BEVDepth: acquisition of reliable depth for multi-view 3D object detection. In: AAAI, pp. 1477\u20131485 (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"9_CR42","doi-asserted-by":"publisher","first-page":"0097","DOI":"10.34133\/cbsystems.0097","volume":"5","author":"Z Li","year":"2024","unstructured":"Li, Z., Zheng, W., Yang, L., Ma, L., Zhou, Y., Peng, Y.: MonoAux: fully exploiting auxiliary information and uncertainty for monocular 3D object detection. Cyborg Bionic Syst. 5, 0097 (2024)","journal-title":"Cyborg Bionic Syst."},{"key":"9_CR43","doi-asserted-by":"crossref","unstructured":"Li, Z., Jia, J., Shi, Y.: MonoLSS: learnable sample selection for monocular 3D detection. In: 3DV, pp. 1125\u20131135 (2024)","DOI":"10.1109\/3DV62453.2024.00088"},{"key":"9_CR44","doi-asserted-by":"crossref","unstructured":"Li, Z., Chen, Z., Li, A., Fang, L., Jiang, Q., Liu, X., Jiang, J.: Unsupervised domain adaptation for monocular 3D object detection via self-training. In: ECCV, vol. 13669, pp. 245\u2013262 (2022)","DOI":"10.1007\/978-3-031-20077-9_15"},{"key":"9_CR45","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: ECCV, vol. 13669, pp. 1\u201318 (2022)","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"9_CR46","doi-asserted-by":"crossref","unstructured":"Li, Z., Qu, Z., Zhou, Y., Liu, J., Wang, H., Jiang, L.: Diversity matters: fully exploiting depth clues for reliable monocular 3D object detection. In: CVPR, pp. 2781\u20132790 (2022)","DOI":"10.1109\/CVPR52688.2022.00281"},{"key":"9_CR47","doi-asserted-by":"crossref","unstructured":"Lian, Q., Li, P., Chen, X.: MonoJSG: joint semantic and geometric cost volume for monocular 3D object detection. In: CVPR, pp. 1060\u20131069 (2022)","DOI":"10.1109\/CVPR52688.2022.00114"},{"key":"9_CR48","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: MonoTAKD: teaching assistant knowledge distillation for monocular 3D object detection. In: CVPR, pp. 22266\u201322275 (2025)","DOI":"10.1109\/CVPR52734.2025.02074"},{"key":"9_CR49","doi-asserted-by":"crossref","unstructured":"Liu, X., Xue, N., Wu, T.: Learning auxiliary monocular contexts helps monocular 3D object detection, pp. 1810\u20131818. AAAI (2022)","DOI":"10.1609\/aaai.v36i2.20074"},{"key":"9_CR50","doi-asserted-by":"crossref","unstructured":"Liu, X., Zheng, C., Cheng, K., Xue, N., Qi, G., Wu, T.: Monocular 3D object detection with bounding box denoising in 3D by perceiver. In: ICCV, pp. 6413\u20136423 (2023)","DOI":"10.1109\/ICCV51070.2023.00592"},{"key":"9_CR51","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhou, D., Lu, F., Fang, J., Zhang, L.: AutoShape: Real-time shape-aware monocular 3D object detection. In: ICCV, pp. 15621\u201315630 (2021)","DOI":"10.1109\/ICCV48922.2021.01535"},{"key":"9_CR52","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts, p. ICLR (2017)"},{"key":"9_CR53","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Geometry uncertainty projection network for monocular 3D object detection. In: ICCV, pp. 3091\u20133101 (2021)","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"9_CR54","unstructured":"Lv, W., Zhao, Y., Chang, Q., Huang, K., Wang, G., Liu, Y.: RT-DETRv2: improved baseline with bag-of-freebies for real-time detection transformer. arXiv:2407.17140 (2024)"},{"key":"9_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/978-3-030-58601-0_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Ma","year":"2020","unstructured":"Ma, X., Liu, S., Xia, Z., Zhang, H., Zeng, X., Ouyang, W.: Rethinking Pseudo-LiDAR Representation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 311\u2013327. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_19"},{"key":"9_CR56","doi-asserted-by":"crossref","unstructured":"Ma, X., et al.: Delving into localization errors for monocular 3D object detection. In: CVPR, pp. 4721\u20134730 (2021)","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"9_CR57","unstructured":"Mansourian, A.M., et al.: A comprehensive survey on knowledge distillation. Trans. Mach. Learn. Res. (2025)"},{"key":"9_CR58","doi-asserted-by":"crossref","unstructured":"Meier, J., Inchingolo, L., Dhaouadi, O., Xia, Y., Kaiser, J., Cremers, D.: MonoCT: overcoming monocular 3D detection domain shift with consistent teacher models. ICRA, pp. 351\u2013358 (2025)","DOI":"10.1109\/ICRA55743.2025.11127874"},{"key":"9_CR59","doi-asserted-by":"crossref","unstructured":"Meier, J., Scalerandi, L., Dhaouadi, O., Kaiser, J., Nikita, A., Cremers, D.: CARLA Drone: monocular 3D object detection from a different perspective. In: GCPR, pp. 137\u2013152 (2024)","DOI":"10.1007\/978-3-031-85187-2_9"},{"issue":"3","key":"9_CR60","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1109\/JAS.2023.123660","volume":"11","author":"C Pan","year":"2024","unstructured":"Pan, C., Peng, J., Zhang, Z.: Depth-guided vision transformer with normalizing flows for monocular 3D object detection. IEEE\/CAA J. Autom. Sinica 11(3), 673\u2013689 (2024)","journal-title":"IEEE\/CAA J. Autom. Sinica"},{"key":"9_CR61","doi-asserted-by":"crossref","unstructured":"Peng, L., et al.: Learning occupancy for monocular 3D object detection. In: CVPR, pp. 10281\u201310292 (2024)","DOI":"10.1109\/CVPR52733.2024.00979"},{"key":"9_CR62","unstructured":"Peng, Y., Li, H., Wu, P., Zhang, Y., Sun, X., Wu, F.: D-FINE: redefine regression task in DETRs as fine-grained distribution refinement. In: ICLR (2025)"},{"key":"9_CR63","doi-asserted-by":"crossref","unstructured":"Pu, F., Wang, Y., Deng, J., Yang, W.: MonoDGP: monocular 3D object detection with decoupled-query and geometry-error priors. In: CVPR, pp. 6520\u20136530 (2025)","DOI":"10.1109\/CVPR52734.2025.00611"},{"key":"9_CR64","doi-asserted-by":"crossref","unstructured":"Ranasinghe, Y., Hegde, D., Patel, V.M.: MonoDiff: monocular 3D object detection and pose estimation with diffusion models. In: CVPR, pp. 10659\u201310670 (2024)","DOI":"10.1109\/CVPR52733.2024.01014"},{"key":"9_CR65","doi-asserted-by":"crossref","unstructured":"Reading, C., Harakeh, A., Chae, J., Waslander, S.L.: Categorical depth distribution network for monocular 3D object detection. In: CVPR, pp. 8555\u20138564 (2021)","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"9_CR66","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS,vol. 28,pp. 91\u201399 (2015)"},{"key":"9_CR67","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120253","volume":"227","author":"M Rezaei","year":"2023","unstructured":"Rezaei, M., Azarmi, M., Mir, F.M.P.: 3D-Net: monocular 3D object recognition for traffic monitoring. Expert Syst. Appl. 227, 120253 (2023)","journal-title":"Expert Syst. Appl."},{"key":"9_CR68","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv:1910.01108 (2019)"},{"key":"9_CR69","doi-asserted-by":"publisher","first-page":"5424","DOI":"10.1109\/TIP.2024.3463409","volume":"33","author":"H Shi","year":"2024","unstructured":"Shi, H., et al.: CoBEV: elevating roadside 3D object detection with depth and height complementarity. IEEE Trans. Image Process. 33, 5424\u20135439 (2024)","journal-title":"IEEE Trans. Image Process."},{"key":"9_CR70","doi-asserted-by":"crossref","unstructured":"Shi, X., Chen, Z., Kim, T.: Multivariate probabilistic monocular 3D object detection, pp. 4270\u20134279. WACV (2023)","DOI":"10.1109\/WACV56688.2023.00426"},{"key":"9_CR71","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: waymo Open Dataset, pp. 2443\u20132451. CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"9_CR72","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: ICML, vol.70,pp. 3319\u20133328 (2017)"},{"key":"9_CR73","doi-asserted-by":"crossref","unstructured":"Tang, Z., et al.: CityFlow: a city-scale benchmark for multi-target multi-camera vehicle tracking and re-identification, pp. 8797\u20138806. CVPR (2019)","DOI":"10.1109\/CVPR.2019.00900"},{"key":"9_CR74","doi-asserted-by":"crossref","unstructured":"Tian, Y., Ye, Q., Doermann, D.S.: YOLOv12: attention-centric real-time object detectors. arXiv:2502.12524 (2025)","DOI":"10.52202\/085713-2627"},{"key":"9_CR75","doi-asserted-by":"crossref","unstructured":"Wang, A., et al.: YOLOv10: real-time end-to-end object detection. In: NeurIPS, vol.\u00a037, pp. 107984\u2013108011 (2024)","DOI":"10.52202\/079017-3429"},{"key":"9_CR76","unstructured":"Wang, L., et al.: Progressive coordinate transforms for monocular 3D object detection. In: NeurIPS, vol.\u00a034, pp. 13364\u201313377 (2021)"},{"key":"9_CR77","doi-asserted-by":"crossref","unstructured":"Wang, S., Xia, C., Lv, F., Shi, Y.: RT-DETRv3: real-time end-to-end object detection with hierarchical dense positive supervision, pp. 1628\u20131636. WACV (2025)","DOI":"10.1109\/WACV61041.2025.00166"},{"key":"9_CR78","doi-asserted-by":"crossref","unstructured":"Wu, Z., Gan, Y., Wu, Y., Wang, R., Wang, X., Pu, J.: FD3D: exploiting foreground depth map for feature-supervised monocular 3D object detection. In: AAAI, pp. 6189\u20136197 (2024)","DOI":"10.1609\/aaai.v38i6.28436"},{"issue":"11","key":"9_CR79","doi-asserted-by":"publisher","first-page":"10295","DOI":"10.1109\/TPAMI.2025.3594805","volume":"47","author":"Z Wu","year":"2025","unstructured":"Wu, Z., et al.: Advancing 3D object detection with depth-aware spatial knowledge distillation. IEEE Trans. Pattern Anal. Mach. Intell. 47(11), 10295\u201310310 (2025)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR80","doi-asserted-by":"crossref","unstructured":"Wu, Z., Wu, Y., Pu, J., Li, X., Wang, X.: Attention-based depth distillation with 3D-aware positional encoding for monocular 3D object detection. In: AAAI, pp. 2892\u20132900 (2023)","DOI":"10.1609\/aaai.v37i3.25391"},{"key":"9_CR81","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: MonoNeRD: NeRF-like representations for monocular 3D object detection. In: CVPR, pp. 6791\u20136801 (2023)","DOI":"10.1109\/ICCV51070.2023.00627"},{"key":"9_CR82","doi-asserted-by":"crossref","unstructured":"Yan, L., Yan, P., Xiong, S., Xiang, X., Tan, Y.: MonoCD: monocular 3D object detection with complementary depths. In: CVPR, pp. 10248\u201310257 (2024)","DOI":"10.1109\/CVPR52733.2024.00976"},{"issue":"2","key":"9_CR83","doi-asserted-by":"publisher","first-page":"3593","DOI":"10.1109\/TIV.2023.3341981","volume":"9","author":"W Yan","year":"2024","unstructured":"Yan, W., Xu, L., Liu, H., Tang, C., Zhou, W.: High-order structural relation distillation networks from LiDAR to monocular image 3D detectors. IEEE Trans. Intell. Veh. 9(2), 3593\u20133604 (2024)","journal-title":"IEEE Trans. Intell. Veh."},{"key":"9_CR84","doi-asserted-by":"crossref","unstructured":"Yang, F., et al.: Geometry-guided domain generalization for monocular 3D object detection, pp. 6467\u20136476. AAAI (2024)","DOI":"10.1609\/aaai.v38i6.28467"},{"key":"9_CR85","first-page":"1","volume":"73","author":"F Yang","year":"2024","unstructured":"Yang, F., He, X., Chen, W., Zhou, P., Li, Z.: MonoPSTR: monocular 3D object detection with dynamic position and scale-aware transformer. IEEE Trans. Instrum. Meas. 73, 1\u201313 (2024)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"9_CR86","doi-asserted-by":"crossref","unstructured":"Yang, Let al.: BEVHeight: a robust framework for vision-based roadside 3D object detection. In: CVPR, pp. 21611\u201321620 (2023)","DOI":"10.1109\/CVPR52729.2023.02070"},{"key":"9_CR87","doi-asserted-by":"crossref","unstructured":"Yang, Y.H., et al.: 3D-MOOD: lifting 2D to 3D for monocular open-set object detection. In: ICCV, pp. 7429\u20137439 (2025)","DOI":"10.1109\/ICCV51701.2025.00697"},{"key":"9_CR88","doi-asserted-by":"crossref","unstructured":"Ye, X., et al.: Rope3D: the roadside perception dataset for autonomous driving and monocular 3D object detection task. In: CVPR, pp. 21309\u201321318 (2022)","DOI":"10.1109\/CVPR52688.2022.02065"},{"key":"9_CR89","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Chun, S., Oh, S.J., Yoo, Y., Choe, J.: CutMix: regularization strategy to train strong classifiers with localizable features. In: ICCV, pp. 6022\u20136031 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"9_CR90","unstructured":"Zhang, H., Ciss\u00e9, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: ICLR (2018)"},{"key":"9_CR91","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Decoupled pseudo-labeling for semi-supervised monocular 3D object detection. In: CVPR, pp. 16923\u201316932 (2024)","DOI":"10.1109\/CVPR52733.2024.01601"},{"key":"9_CR92","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: MonoDETR: depth-guided transformer for monocular 3D object detection. In: CVPR, pp. 9121\u20139132 (2023)","DOI":"10.1109\/ICCV51070.2023.00840"},{"key":"9_CR93","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, J., Zhou, J.: Objects are different: flexible monocular 3D object detection. In: CVPR, pp. 3289\u20133298 (2021)","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"9_CR94","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: DETRs beat YOLOs on real-time object detection. In: CVPR, pp. 16965\u201316974 (2024)","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"9_CR95","unstructured":"Zhenyu, L., et al.: Towards model generalization for monocular 3D object detection. arXiv:2205.11664 (2022)"},{"key":"9_CR96","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Liu, Q., Zhu, H., Li, Y., Chang, S., Guo, M.: Exploiting ground depth estimation for mobile monocular 3D object detection. IEEE Trans. Pattern Anal. Mach. Intell. 47(4), (2025)","DOI":"10.1109\/TPAMI.2025.3529084"},{"key":"9_CR97","doi-asserted-by":"crossref","unstructured":"Zhu, X., et al.: RoScenes: a large-scale multi-view 3D dataset for roadside perception. In: ECCV, vol. 15099,pp. 331\u2013347 (2024)","DOI":"10.1007\/978-3-031-72940-9_19"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37232-1_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:51:56Z","timestamp":1788933116000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37232-1_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372314","9783032372321"],"references-count":97,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37232-1_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}