{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T15:12:58Z","timestamp":1778857978919,"version":"3.51.4"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 62576269"],"award-info":[{"award-number":["No. 62576269"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1007\/s00138-026-01806-z","type":"journal-article","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T16:34:29Z","timestamp":1775061269000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DKM-Net: self-supervised 3D occupancy prediction via multi-scale dynamic kernel method"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9198-7554","authenticated-orcid":false,"given":"Huipeng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4929-1887","authenticated-orcid":false,"given":"Xuyi","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8119-3726","authenticated-orcid":false,"given":"Kuizhi","family":"Mei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,1]]},"reference":[{"key":"1806_CR1","unstructured":"Gan, W., Mo, N., Xu, H., et\u00a0al.: A simple framework for 3D occupancy estimation in autonomous driving (2023). arxiv:2303.10076"},{"key":"1806_CR2","doi-asserted-by":"crossref","unstructured":"Jiang, B., Chen, S., Xu, Q., et\u00a0al.: VAD: vectorized scene representation for efficient autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8340\u20138350 (2023)","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"1806_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102671","volume":"114","author":"H Xu","year":"2025","unstructured":"Xu, H., Chen, J., Meng, S., et al.: A survey on occupancy perception for autonomous driving: the information fusion perspective. Inf. Fusion 114, 102671 (2025)","journal-title":"Inf. Fusion"},{"key":"1806_CR4","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, W., Li, H., et\u00a0al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers (2022). arxiv:2203.17270","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"1806_CR5","doi-asserted-by":"crossref","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: European Conference on Computer Vision, pp. 194\u2013210. Springer (2020)","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"1806_CR6","unstructured":"Ng, M.H., Radia, K., Chen, J., et\u00a0al.: BEV-Seg: Bird\u2019s eye view semantic segmentation using geometry and semantic point cloud (2020). arxiv:2006.11436"},{"key":"1806_CR7","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zheng, W., Zhang, Y., et\u00a0al.: Tri-perspective view for vision-based 3D semantic occupancy prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9223\u20139232 (2023)","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"1806_CR8","doi-asserted-by":"crossref","unstructured":"Sirko-Galouchenko, S., Boulch, A., Gidaris, S., et\u00a0al.: OccFeat: self-supervised occupancy feature prediction for pretraining BEV segmentation networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4493\u20134503 (2024)","DOI":"10.1109\/CVPRW63382.2024.00452"},{"key":"1806_CR9","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zheng, W., Zhang, B., et\u00a0al.: SelfOcc: self-supervised vision-based 3D occupancy prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19946\u201319956 (2024)","DOI":"10.1109\/CVPR52733.2024.01885"},{"key":"1806_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et\u00a0al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1806_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., et\u00a0al.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1806_CR12","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhang, J., Wang, Z., et\u00a0al.: Vision-based 3D occupancy prediction in autonomous driving: a review and outlook (2024). arxiv:2405.02595","DOI":"10.1007\/s11704-024-40443-5"},{"key":"1806_CR13","doi-asserted-by":"crossref","unstructured":"Shu, C., Yu, K., Duan, Z., et\u00a0al.: Feature-metric loss for self-supervised learning of depth and egomotion. In: European Conference on Computer Vision, pp. 572\u2013588. Springer (2020)","DOI":"10.1007\/978-3-030-58529-7_34"},{"key":"1806_CR14","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhao, L., Zheng, W., et\u00a0al.: SurroundOcc: multi-camera 3D occupancy prediction for autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21729\u201321740 (2023)","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"1806_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, C., Yan, J., Wei, Y., et\u00a0al.: OccNeRF: advancing 3D occupancy prediction in lidar-free environments (2024). arxiv:2312.09243","DOI":"10.1109\/TIP.2025.3567828"},{"issue":"1","key":"1806_CR16","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., et al.: NeRF: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"1806_CR17","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Tancik, M., et\u00a0al.: Mip-NeRF: a multiscale representation for anti-aliasing neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5855\u20135864 (2021)","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"1806_CR18","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., et\u00a0al.: Zip-neRF: anti-aliased grid-based neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19697\u201319705 (2023)","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"1806_CR19","unstructured":"Zhang, K., Riegler, G., Snavely, N., et\u00a0al.: NeRF++: analyzing and improving neural radiance fields (2020). arxiv:2010.07492"},{"key":"1806_CR20","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., et\u00a0al.: Mip-NeRF: Unbounded anti-aliased neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5470\u20135479 (2022)","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"1806_CR21","doi-asserted-by":"crossref","unstructured":"Wimbauer, F., Yang, N., Rupprecht, C., et\u00a0al.: Behind the scenes: density fields for single view reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 9076\u20139086 (2023)","DOI":"10.1109\/CVPR52729.2023.00876"},{"key":"1806_CR22","doi-asserted-by":"crossref","unstructured":"Cao, A.Q., De\u00a0Charette, R.: SceneRF: self-supervised monocular 3D scene reconstruction with radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9387\u20139398 (2023)","DOI":"10.1109\/ICCV51070.2023.00861"},{"key":"1806_CR23","doi-asserted-by":"crossref","unstructured":"Ye, X., Zhao, W., Liu, T., et\u00a0al.: Constraining depth map geometry for multi-view stereo: a dual-depth approach with saddle-shaped depth cells. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17661\u201317670 (2023)","DOI":"10.1109\/ICCV51070.2023.01619"},{"key":"1806_CR24","unstructured":"Gong, K., Yin, Z., Li, Y., et\u00a0al.: Dynamic shuffle: an efficient channel mixture method (2023). arxiv:2310.02776"},{"key":"1806_CR25","doi-asserted-by":"crossref","unstructured":"Oechsle, M., Peng, S., Geiger, A.: UNISURF: unifying neural implicit surfaces and radiance fields for multi-view reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5589\u20135599 (2021)","DOI":"10.1109\/ICCV48922.2021.00554"},{"key":"1806_CR26","unstructured":"Wang, P., Liu, L., Liu, Y., et\u00a0al.: NeuS: learning neural implicit surfaces by volume rendering for multi-view reconstruction (2023). arxiv:2106.10689"},{"key":"1806_CR27","first-page":"4805","volume":"34","author":"L Yariv","year":"2021","unstructured":"Yariv, L., Gu, J., Kasten, Y., et al.: Volume rendering of neural implicit surfaces. Adv. Neural. Inf. Process. Syst. 34, 4805\u20134815 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1806_CR28","doi-asserted-by":"crossref","unstructured":"Nguyen, K., Dang, T., Huber, M.: Volumetric mapping with panoptic refinement using kernel density estimation for mobile robots. In: 2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 9824\u20139830. IEEE (2024)","DOI":"10.1109\/IROS58592.2024.10802224"},{"key":"1806_CR29","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A.H., et\u00a0al.: nuscenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"1806_CR30","first-page":"64318","volume":"36","author":"X Tian","year":"2023","unstructured":"Tian, X., Jiang, T., Yun, L., et al.: Occ3D: a large-scale 3D occupancy prediction benchmark for autonomous driving. Adv. Neural. Inf. Process. Syst. 36, 64318\u201364330 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1806_CR31","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2017). arxiv:1412.6980"},{"key":"1806_CR32","unstructured":"Gan, W., Mo, N., Xu, H., et\u00a0al.: A simple framework for 3d occupancy estimation in autonomous driving. (2023) arxiv:2303.10076"},{"key":"1806_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, F., Zou, X., et\u00a0al.: A simple framework for open-vocabulary segmentation and detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1020\u20131031 (2023)","DOI":"10.1109\/ICCV51070.2023.00100"},{"issue":"2","key":"1806_CR34","doi-asserted-by":"publisher","first-page":"5397","DOI":"10.1109\/LRA.2022.3150884","volume":"7","author":"V Guizilini","year":"2022","unstructured":"Guizilini, V., Vasiljevic, I., Ambrus, R., et al.: Full surround monodepth from multiple cameras. IEEE Robot. Autom. Lett. 7(2), 5397\u20135404 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"1806_CR35","first-page":"4032","volume":"35","author":"JH Kim","year":"2022","unstructured":"Kim, J.H., Hur, J., Nguyen, T.P., et al.: Self-supervised surround-view depth estimation with volumetric feature fusion. Adv. Neural. Inf. Process. Syst. 35, 4032\u20134045 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1806_CR36","unstructured":"Wei, Y., Zhao, L., Zheng, W., et\u00a0al.: SurroundDepth: entangling surrounding views for self-supervised multi-camera depth estimation. In: Conference on Robot Learning, pp. 539\u2013549. PMLR (2023)"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-026-01806-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-026-01806-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-026-01806-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T14:31:51Z","timestamp":1778855511000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-026-01806-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,1]]},"references-count":36,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["1806"],"URL":"https:\/\/doi.org\/10.1007\/s00138-026-01806-z","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,1]]},"assertion":[{"value":"11 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 February 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 April 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"49"}}