{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:23:51Z","timestamp":1757622231523,"version":"3.44.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T00:00:00Z","timestamp":1754352000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T00:00:00Z","timestamp":1754352000000},"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":["61673396"],"award-info":[{"award-number":["61673396"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2022MF260"],"award-info":[{"award-number":["ZR2022MF260"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-07697-7","type":"journal-article","created":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T10:19:14Z","timestamp":1754389154000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ReDepthNet: a radar and camera depth estimation model based on semantic segmentation mask region alignment"],"prefix":"10.1007","volume":"81","author":[{"given":"Hong","family":"Liang","sequence":"first","affiliation":[]},{"given":"Xu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Mingwen","family":"Shao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,5]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Chen X, Zhang T, Wang Y, et\u00a0al (2023) Futr3d: a unified sensor fusion framework for 3d detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 172\u2013181","key":"7697_CR1","DOI":"10.1109\/CVPRW59228.2023.00022"},{"doi-asserted-by":"crossref","unstructured":"Huang Y, Zheng W, Zhang Y, et\u00a0al (2023) 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","key":"7697_CR2","DOI":"10.1109\/CVPR52729.2023.00890"},{"doi-asserted-by":"crossref","unstructured":"Maier D, Hornung A, Bennewitz M (2012) Real-time navigation in 3D environments based on depth camera data. In: 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012), pp. 692\u2013697. IEEE","key":"7697_CR3","DOI":"10.1109\/HUMANOIDS.2012.6651595"},{"unstructured":"Saxena A, Chung S, Ng A (2005) Learning depth from single monocular images. Advances in Neural Information Processing Systems 18","key":"7697_CR4"},{"unstructured":"Teed Z, Deng J (2018) Deepv2d: video to depth with differentiable structure from motion. arXiv preprint arXiv:1812.04605","key":"7697_CR5"},{"unstructured":"Birkl R, Wofk D, M\u00fcller M (2023) Midas v3.1\u2013a model zoo for robust monocular relative depth estimation. arXiv preprint arXiv:2307.14460","key":"7697_CR6"},{"doi-asserted-by":"crossref","unstructured":"Nobis F, Geisslinger M, Weber M, et\u00a0al (2019) A deep learning-based radar and camera sensor fusion architecture for object detection. In: 2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF), pp. 1\u20137. IEEE","key":"7697_CR7","DOI":"10.1109\/SDF.2019.8916629"},{"doi-asserted-by":"crossref","unstructured":"Lo CC, Vandewalle P (2021) Depth estimation from monocular images and sparse radar using deep ordinal regression network. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 3343\u20133347. IEEE","key":"7697_CR8","DOI":"10.1109\/ICIP42928.2021.9506550"},{"doi-asserted-by":"crossref","unstructured":"Sun H, Feng H, Mauro G, et al (2024) Enhanced radar perception via multi-task learning: Towards refined data for sensor fusion applications. arXiv preprint arXiv:2404.06165","key":"7697_CR9","DOI":"10.1109\/IV55156.2024.10588795"},{"doi-asserted-by":"crossref","unstructured":"Singh AD, Ba Y, Sarker A, Zhang H, Kadambi A, Soatto S, Srivastava M, Wong A (2023) Depth estimation from camera image and mmwave radar point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9275\u20139285","key":"7697_CR10","DOI":"10.1109\/CVPR52729.2023.00895"},{"doi-asserted-by":"crossref","unstructured":"Li H, Jing M, Liang J, Fan H, Ji R (2023) Sparse beats dense: rethinking supervision in radar-camera depth completion. arxiv:2312.00844","key":"7697_CR11","DOI":"10.1007\/978-3-031-72967-6_8"},{"doi-asserted-by":"publisher","unstructured":"Ouyang D, He S, Zhang G, Luo M, Guo H, Zhan J, Huang Z (2023) Efficient multi-scale attention module with cross-spatial learning. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10096516","key":"7697_CR12","DOI":"10.1109\/ICASSP49357.2023.10096516"},{"doi-asserted-by":"crossref","unstructured":"Caesar H, Bankiti V, Lang AH, Vora S, Liong VE, Xu Q, Krishnan A, Pan Y, Baldan G, Beijbom O (2020) nuscenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631","key":"7697_CR13","DOI":"10.1109\/CVPR42600.2020.01164"},{"doi-asserted-by":"crossref","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125","key":"7697_CR14","DOI":"10.1109\/CVPR.2017.106"},{"doi-asserted-by":"crossref","unstructured":"Long Y, Morris D, Liu X, Castro M, Chakravarty P, Narayanan P (2021) Radar-camera pixel depth association for depth completion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12507\u201312516","key":"7697_CR15","DOI":"10.1109\/CVPR46437.2021.01232"},{"doi-asserted-by":"crossref","unstructured":"Sun H, Feng H, Ott J, Servadei L, Wille R (2024) Cafnet: a confidence-driven framework for radar camera depth estimation. In: 2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2734\u20132740. IEEE","key":"7697_CR16","DOI":"10.1109\/IROS58592.2024.10801594"},{"doi-asserted-by":"crossref","unstructured":"Li H, Ma Y, Gu Y, Hu K, Liu Y, Zuo X (2024) Radarcam-depth: Radar-camera fusion for depth estimation with learned metric scale. arXiv preprint arXiv:2401.04325","key":"7697_CR17","DOI":"10.1109\/ICRA57147.2024.10610929"},{"doi-asserted-by":"crossref","unstructured":"Imran S, Liu X, Morris D (2021) Depth completion with twin surface extrapolation at occlusion boundaries. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2583\u20132592","key":"7697_CR18","DOI":"10.1109\/CVPR46437.2021.00261"},{"doi-asserted-by":"crossref","unstructured":"Qiu J, Cui Z, Zhang Y, Zhang X, Liu S, Zeng B, Pollefeys M (2019) Deeplidar: Deep surface normal guided depth prediction for outdoor scene from sparse lidar data and single color image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3313\u20133322","key":"7697_CR19","DOI":"10.1109\/CVPR.2019.00343"},{"doi-asserted-by":"crossref","unstructured":"Rho K, Ha J, Kim Y (2022) Guideformer: transformers for image guided depth completion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6250\u20136259","key":"7697_CR20","DOI":"10.1109\/CVPR52688.2022.00615"},{"unstructured":"Eigen D, Puhrsch C, Fergus R (2014) Depth map prediction from a single image using a multi-scale deep network. Advances in Neural Information Processing Systems 27","key":"7697_CR21"},{"doi-asserted-by":"crossref","unstructured":"Xie J, Lei C, Li Z, Li LE, Chen Q (2020) Video depth estimation by fusing flow-to-depth proposals. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 10100\u201310107. IEEE","key":"7697_CR22","DOI":"10.1109\/IROS45743.2020.9341659"},{"issue":"17","key":"7697_CR23","doi-asserted-by":"publisher","first-page":"25099","DOI":"10.1007\/s11227-024-06388-z","volume":"80","author":"Q Zhang","year":"2024","unstructured":"Zhang Q, Song Y, Lou H (2024) Tl-depth: monocular depth estimation based on tower connections and laplacian-filtering residual completion. J Supercomput 80(17):25099\u201325117","journal-title":"J Supercomput"},{"doi-asserted-by":"crossref","unstructured":"Zhang F, Yu Z, Li C, Zhang R, Bai X, Zhou Z, Cao S-Y, Wang W, Shen H-L (2025) Structure-aware radar-camera depth estimation. arXiv e-prints, 2506\u201305008 arXiv:2506.05008 [cs.CV]","key":"7697_CR24","DOI":"10.1109\/ICRA55743.2025.11128760"},{"unstructured":"Chen Z, Duan Y, Wang W, et al (2022) Vision transformer adapter for dense predictions. arXiv preprint arXiv:2205.08534","key":"7697_CR25"},{"key":"7697_CR26","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou B, Zhao H, Puig X, Xiao T, Fidler S, Barriuso A, Torralba A (2019) Semantic understanding of scenes through the ADE20K dataset. Int J Comput Vis 127:302\u2013321","journal-title":"Int J Comput Vis"},{"doi-asserted-by":"crossref","unstructured":"Xie S, Girshick R, Doll\u00e1r P, Tu Z, He K (2017) Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500","key":"7697_CR27","DOI":"10.1109\/CVPR.2017.634"},{"unstructured":"Kingma DP (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980","key":"7697_CR28"},{"doi-asserted-by":"crossref","unstructured":"Sun H, Vysotskaya N, Sukianto T, Feng H, Ott J, Peng X, Servadei L, Wille R (2025) Lircdepth: Lightweight radar-camera depth estimation via knowledge distillation and uncertainty guidance. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE","key":"7697_CR29","DOI":"10.1109\/ICASSP49660.2025.10889898"},{"doi-asserted-by":"crossref","unstructured":"Ma F, Karaman S (2018) Sparse-to-dense: Depth prediction from sparse depth samples and a single image. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 4796\u20134803. IEEE","key":"7697_CR30","DOI":"10.1109\/ICRA.2018.8460184"},{"doi-asserted-by":"crossref","unstructured":"Wang T-H, Wang F-E, Lin J-T, Tsai Y-H, Chiu W-C, Sun M (2018) Plug-and-play: Improve depth estimation via sparse data propagation. arXiv preprint arXiv:1812.08350","key":"7697_CR31","DOI":"10.1109\/ICRA.2019.8794404"},{"doi-asserted-by":"crossref","unstructured":"Gasperini S, Koch P, Dallabetta V, Navab N, Busam B, Tombari F (2021) R4dyn: exploring radar for self-supervised monocular depth estimation of dynamic scenes. In: 2021 International Conference on 3D Vision (3DV), pp. 751\u2013760. IEEE","key":"7697_CR32","DOI":"10.1109\/3DV53792.2021.00084"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07697-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-07697-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07697-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T18:36:26Z","timestamp":1757356586000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-07697-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,5]]},"references-count":32,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["7697"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-07697-7","relation":{},"ISSN":["1573-0484"],"issn-type":[{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2025,8,5]]},"assertion":[{"value":"19 July 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 August 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"1215"}}