{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T10:54:47Z","timestamp":1774695287137,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T00:00:00Z","timestamp":1774656000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T00:00:00Z","timestamp":1774656000000},"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":["J Supercomput"],"DOI":"10.1007\/s11227-026-08461-1","type":"journal-article","created":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T10:34:48Z","timestamp":1774694088000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Joint depth estimation and multi-model SLAM for robust perception in structure-degraded environments"],"prefix":"10.1007","volume":"82","author":[{"given":"Weipeng","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxuan","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoguang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zichong","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqi","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,28]]},"reference":[{"issue":"5","key":"8461_CR1","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1109\/TRO.2017.2705103","volume":"33","author":"R Mur-Artal","year":"2017","unstructured":"Mur-Artal R, Tard\u00f3s JD (2017) ORB-SLAM2: an open-source SLAM system for monocular, stereo, and RGB-D cameras. IEEE Trans Rob 33(5):1255\u20131262. https:\/\/doi.org\/10.1109\/TRO.2017.2705103","journal-title":"IEEE Trans Rob"},{"key":"8461_CR2","doi-asserted-by":"publisher","unstructured":"Engel J, Sch\u00f6ps T, Cremers D (2014) LSD-SLAM: large-scale direct monocular SLAM. In: European conference on computer vision (ECCV), pp. 834\u2013849. https:\/\/doi.org\/10.1007\/978-3-319-10605-2_54","DOI":"10.1007\/978-3-319-10605-2_54"},{"key":"8461_CR3","doi-asserted-by":"crossref","unstructured":"Zhang J, Singh S (2014) LOAM: Lidar odometry and mapping in real-time. In: Robotics: science and systems (RSS), pp. 1\u20139","DOI":"10.15607\/RSS.2014.X.007"},{"key":"8461_CR4","doi-asserted-by":"publisher","unstructured":"Shao W, Vijayarangan S, Li C, Kantor G (2019) Stereo visual inertial LiDAR simultaneous localization and mapping. In: IEEE\/RSJ international conference on intelligent robots and systems (IROS), pp. 370\u2013377. https:\/\/doi.org\/10.1109\/IROS40897.2019.8968012","DOI":"10.1109\/IROS40897.2019.8968012"},{"key":"8461_CR5","doi-asserted-by":"publisher","unstructured":"Chen C, Rosa S, Miao Y, Lu CX, Wu W, Markham A, Trigoni N (2019) Selective sensor fusion for neural visual-inertial odometry. In: IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 10534\u201310543. https:\/\/doi.org\/10.1109\/CVPR.2019.01079","DOI":"10.1109\/CVPR.2019.01079"},{"key":"8461_CR6","doi-asserted-by":"publisher","unstructured":"Chen C, Rosa S, Miao Y, Lu CX, Wu W, Markham A, Trigoni N (2019) Selective sensor fusion for neural visual-inertial odometry. In: IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 10534\u201310543. https:\/\/doi.org\/10.1109\/CVPR.2019.01079","DOI":"10.1109\/CVPR.2019.01079"},{"issue":"4","key":"8461_CR7","doi-asserted-by":"publisher","first-page":"1004","DOI":"10.1109\/TRO.2018.2853729","volume":"34","author":"T Qin","year":"2018","unstructured":"Qin T, Li P, Shen S (2018) VINS-Mono: a robust and versatile monocular visual-inertial state estimator. IEEE Trans Rob 34(4):1004\u20131020. https:\/\/doi.org\/10.1109\/TRO.2018.2853729","journal-title":"IEEE Trans Rob"},{"issue":"3","key":"8461_CR8","doi-asserted-by":"publisher","first-page":"4103","DOI":"10.1109\/TNNLS.2022.3176677","volume":"36","author":"C Chen","year":"2025","unstructured":"Chen C, Rosa S, Lu CX, Wang B, Trigoni N, Markham A (2025) Learning selective sensor fusion for state estimation. IEEE Trans Neural Netw Learn Syst 36(3):4103\u20134117. https:\/\/doi.org\/10.1109\/TNNLS.2022.3176677","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"6","key":"8461_CR9","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.1109\/TRO.2021.3075644","volume":"37","author":"C Campos","year":"2021","unstructured":"Campos C, Elvira R, Rodr\u00edguez JJG, Montiel JMM, Tard\u00f3s JD (2021) ORB-SLAM3: an accurate open-source library for visual, visual-inertial, and multimap SLAM. IEEE Trans Rob 37(6):1874\u20131890. https:\/\/doi.org\/10.1109\/TRO.2021.3075644","journal-title":"IEEE Trans Rob"},{"issue":"12","key":"8461_CR10","doi-asserted-by":"publisher","first-page":"747","DOI":"10.3390\/biomimetics9120747","volume":"9","author":"SM Yasir","year":"2024","unstructured":"Yasir SM, Ahn H (2024) Deep neural networks for accurate depth estimation with latent space features. Biomimetics 9(12):747. https:\/\/doi.org\/10.3390\/biomimetics9120747","journal-title":"Biomimetics"},{"key":"8461_CR11","unstructured":"Eigen D, Puhrsch C, Fergus R (2014) Depth map prediction from a single image using a multi-scale deep network. In: Advances in neural information processing systems (NeurIPS), vol. 27, pp. 2366\u20132374"},{"key":"8461_CR12","doi-asserted-by":"publisher","unstructured":"Godard C, Mac Aodha O, Firman M, Brostow GJ (2019) Digging into self-supervised monocular depth estimation. In: IEEE\/CVF international conference on computer vision (ICCV), pp. 3828\u20133838. https:\/\/doi.org\/10.1109\/ICCV.2019.00393","DOI":"10.1109\/ICCV.2019.00393"},{"key":"8461_CR13","doi-asserted-by":"publisher","unstructured":"Ranftl R, Bochkovskiy A, Koltun V (2021) Vision transformers for dense prediction. In: IEEE\/CVF international conference on computer vision (ICCV), pp. 12159\u201312168. https:\/\/doi.org\/10.1109\/ICCV48922.2021.01196","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"8461_CR14","doi-asserted-by":"publisher","unstructured":"Tateno K, Tombari F, Laina I, Navab N (2017) CNN-SLAM: real-time dense monocular SLAM with learned depth prediction. In: IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 6565\u20136574. https:\/\/doi.org\/10.1109\/CVPR.2017.695","DOI":"10.1109\/CVPR.2017.695"},{"issue":"4","key":"8461_CR15","doi-asserted-by":"publisher","first-page":"4076","DOI":"10.1109\/LRA.2018.2860039","volume":"3","author":"B Bescos","year":"2018","unstructured":"Bescos B, F\u00e1cil JM, Civera J, Neira J (2018) DynaSLAM: tracking, mapping, and inpainting in dynamic scenes. IEEE Robot Autom Lett 3(4):4076\u20134083. https:\/\/doi.org\/10.1109\/LRA.2018.2860039","journal-title":"IEEE Robot Autom Lett"},{"key":"8461_CR16","doi-asserted-by":"publisher","unstructured":"Tiwari L, Ji P, Tran Q-H, Zhuang B, Anand S, Chandraker M (2020) Pseudo RGB-D for self-improving monocular SLAM and depth prediction. In: European conference on computer vision (ECCV), pp. 437\u2013455. https:\/\/doi.org\/10.1007\/978-3-030-58621-8_26","DOI":"10.1007\/978-3-030-58621-8_26"},{"key":"8461_CR17","doi-asserted-by":"publisher","unstructured":"Xing X, Cai Y, Lu T, Yang Y, Wen D (2022) Joint self-supervised monocular depth estimation and SLAM. In: international conference on pattern recognition (ICPR), pp. 4030\u20134036. https:\/\/doi.org\/10.1109\/ICPR56361.2022.9956576","DOI":"10.1109\/ICPR56361.2022.9956576"},{"key":"8461_CR18","doi-asserted-by":"publisher","unstructured":"Shan T, Englot B, Ratti C, Rus D (2021) LVI-SAM: Tightly-coupled LiDAR-visual-inertial odometry via smoothing and mapping. In: IEEE international conference on robotics and automation (ICRA), pp. 5692\u20135698. https:\/\/doi.org\/10.1109\/ICRA48506.2021.9561996","DOI":"10.1109\/ICRA48506.2021.9561996"},{"issue":"4","key":"8461_CR19","doi-asserted-by":"publisher","first-page":"2053","DOI":"10.1109\/TRO.2022.3141876","volume":"38","author":"W Xu","year":"2022","unstructured":"Xu W, Cai Y, He D, Lin J, Zhang F (2022) FAST-LIO2: fast direct LiDAR-inertial odometry. IEEE Trans Rob 38(4):2053\u20132073. https:\/\/doi.org\/10.1109\/TRO.2022.3141876","journal-title":"IEEE Trans Rob"},{"issue":"12","key":"8461_CR20","doi-asserted-by":"publisher","first-page":"11168","DOI":"10.1109\/TPAMI.2024.3456473","volume":"46","author":"J Lin","year":"2024","unstructured":"Lin J, Zhang F (2024) R$$^{3}$$LIVE++: a robust, real-time, radiance reconstruction package with a tightly-coupled LiDAR-inertial-visual state estimator. IEEE Trans Pattern Anal Mach Intell 46(12):11168\u201311185. https:\/\/doi.org\/10.1109\/TPAMI.2024.3456473","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8461_CR21","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1109\/TRO.2024.3502198","volume":"41","author":"C Zheng","year":"2025","unstructured":"Zheng C, Xu W, Zou Z, Hua T, Yuan C, He D, Zhou B, Liu Z, Lin J, Zhu F, Ren Y, Wang R, Meng F, Zhang F (2025) FAST-LIVO2: fast, direct LiDAR-inertial-visual odometry. IEEE Trans Rob 41:326\u2013346. https:\/\/doi.org\/10.1109\/TRO.2024.3502198","journal-title":"IEEE Trans Rob"},{"key":"8461_CR22","doi-asserted-by":"publisher","unstructured":"Lee JH, Han MK, Ko DW, Suh IH (2019) From big to small: multi-scale local planar guidance for monocular depth estimation. arXiv preprint arXiv:1907.10326. https:\/\/doi.org\/10.48550\/arXiv.1907.10326","DOI":"10.48550\/arXiv.1907.10326"},{"key":"8461_CR23","doi-asserted-by":"publisher","unstructured":"Aleotti F, Tosi F, Poggi M, Mattoccia S (2018) Generative adversarial networks for unsupervised monocular depth prediction. In: European conference on computer vision (ECCV), pp. 337\u2013354. https:\/\/doi.org\/10.1007\/978-3-030-11009-3_20","DOI":"10.1007\/978-3-030-11009-3_20"},{"key":"8461_CR24","doi-asserted-by":"publisher","unstructured":"Shi Z, Shen Y, Zhu J, Yeung D-Y, Chen Q (2022) 3D-Aware indoor scene synthesis with depth priors. In: European conference on computer vision (ECCV), pp. 406\u2013422. https:\/\/doi.org\/10.1007\/978-3-031-19787-1_23","DOI":"10.1007\/978-3-031-19787-1_23"},{"issue":"12","key":"8461_CR25","doi-asserted-by":"publisher","first-page":"1551","DOI":"10.1145\/3690826","volume":"20","author":"C Liu","year":"2024","unstructured":"Liu C, Chen Y, Zhu M, Hao C, Li H, Wang X (2024) DEGAN: detail-enhanced generative adversarial network for monocular depth-based 3D reconstruction. ACM Trans Multimed Comput Commun Appl 20(12):1551\u20131578. https:\/\/doi.org\/10.1145\/3690826","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"8461_CR26","doi-asserted-by":"publisher","unstructured":"Taghavi P, Langari R, Pandey G (2024) SwinMTL: A shared architecture for simultaneous depth estimation and semantic segmentation from monocular camera images. In: IEEE\/RSJ international conference on intelligent robots and systems (IROS), pp. 4957\u20134964. https:\/\/doi.org\/10.1109\/IROS58592.2024.10802239","DOI":"10.1109\/IROS58592.2024.10802239"},{"key":"8461_CR27","doi-asserted-by":"publisher","first-page":"3964","DOI":"10.1109\/TIP.2024.3416065","volume":"33","author":"Z Li","year":"2024","unstructured":"Li Z, Wang X, Liu X, Jiang J (2024) BinsFormer: revisiting adaptive bins for monocular depth estimation. IEEE Trans Image Process 33:3964\u20133976. https:\/\/doi.org\/10.1109\/TIP.2024.3416065","journal-title":"IEEE Trans Image Process"},{"key":"8461_CR28","doi-asserted-by":"publisher","unstructured":"Yang L, Kang B, Huang Z, Xu X, Feng J, Zhao H (2024) Depth anything: unleashing the power of large-scale unlabeled data. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10371\u201310381. https:\/\/doi.org\/10.1109\/CVPR52733.2024.00987","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"8461_CR29","doi-asserted-by":"publisher","unstructured":"Li Y, Yu AW, Meng T, Caine B, Ngiam J, Peng D, Shen J, Lu Y, Zhou D, Le QV, Yuille A, Tan M (2022) DeepFusion: lidar-camera deep fusion for multi-modal 3D object detection. In: IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 17182\u201317191. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01667","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"8461_CR30","doi-asserted-by":"publisher","unstructured":"Ji P, Yan Q, Ma Y, Xu Y (2022) GeoRefine: self-supervised online depth refinement for accurate dense mapping. In: European conference on computer vision (ECCV), pp. 360\u2013377. https:\/\/doi.org\/10.1007\/978-3-031-19769-7_21","DOI":"10.1007\/978-3-031-19769-7_21"},{"key":"8461_CR31","doi-asserted-by":"publisher","unstructured":"Shan T, Englot B, Meyers D, Wang W, Ratti C, Rus D (2020) LIO-SAM: tightly-coupled LiDAR-inertial odometry via smoothing and mapping. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5135\u20135142. https:\/\/doi.org\/10.1109\/IROS45743.2020.9341176","DOI":"10.1109\/IROS45743.2020.9341176"},{"key":"8461_CR32","doi-asserted-by":"publisher","unstructured":"Behley J, Stachniss C (2018) Efficient surfel-based SLAM using 3D laser range data in urban environments. In: Robotics: science and systems (RSS). https:\/\/doi.org\/10.15607\/RSS.2018.XIV.016","DOI":"10.15607\/RSS.2018.XIV.016"},{"key":"8461_CR33","doi-asserted-by":"publisher","unstructured":"Kohlbrecher S, von Stryk O, Meyer J, Klingauf U (2011) A flexible and scalable SLAM system with full 3D motion estimation. In: IEEE international symposium on safety, security, and rescue robotics (SSRR), pp. 155\u2013160. https:\/\/doi.org\/10.1109\/SSRR.2011.6106777","DOI":"10.1109\/SSRR.2011.6106777"},{"key":"8461_CR34","doi-asserted-by":"publisher","unstructured":"Triggs B, McLauchlan PF, Hartley RI, Fitzgibbon AW (2000) Bundle adjustment \u2013 a modern synthesis. In: International workshop on vision algorithms, pp. 298\u2013372. https:\/\/doi.org\/10.1007\/3-540-44480-7_21","DOI":"10.1007\/3-540-44480-7_21"},{"key":"8461_CR35","doi-asserted-by":"publisher","unstructured":"Zhou Y, Kar A, Turner E, Kowdle A, Guo CX, DuToit RC, Tsotsos K (2022) Learned monocular depth priors in visual-inertial initialization. In: European conference on computer vision (ECCV), pp. 552\u2013570. https:\/\/doi.org\/10.1007\/978-3-031-20047-2_32","DOI":"10.1007\/978-3-031-20047-2_32"},{"key":"8461_CR36","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1007\/s00034-019-01173-3","volume":"39","author":"M Geng","year":"2020","unstructured":"Geng M, Shang S, Ding B, Wang H, Zhang P (2020) Unsupervised learn-based depth estimation-aided visual SLAM approach. Circ Syst Signal Process 39:543\u2013570. https:\/\/doi.org\/10.1007\/s00034-019-01173-3","journal-title":"Circ Syst Signal Process"},{"key":"8461_CR37","doi-asserted-by":"publisher","unstructured":"Kasyanov A, Engelmann F, St\u00fcckler J, Leibe B (2017) Keyframe-based visual-inertial online SLAM with relocalization. In: IEEE\/RSJ international conference on intelligent robots and systems (IROS), pp. 6662\u20136669. https:\/\/doi.org\/10.1109\/IROS.2017.8206581","DOI":"10.1109\/IROS.2017.8206581"},{"key":"8461_CR38","unstructured":"Teed Z, Deng J (2021) DROID-SLAM: Deep visual SLAM for monocular, stereo, and RGB-D cameras. In: Advances in neural information processing systems (NeurIPS), vol. 34, pp. 16558\u201316569"},{"key":"8461_CR39","doi-asserted-by":"publisher","unstructured":"Zheng C, Zhu Q, Xu W, Liu X, Guo Q, Zhang F (2022) FAST-LIVO: Fast and tightly-coupled sparse-direct LiDAR-inertial-visual odometry. In: IEEE\/RSJ international conference on intelligent robots and systems (IROS), pp. 4003\u20134009. https:\/\/doi.org\/10.1109\/IROS47612.2022.9981107","DOI":"10.1109\/IROS47612.2022.9981107"},{"key":"8461_CR40","doi-asserted-by":"publisher","unstructured":"Wang H, Wang C, Chen C-L, Xie L (2021) F-LOAM: fast LiDAR odometry and mapping. In: IEEE\/RSJ international conference on intelligent robots and systems (IROS), pp. 4390\u20134396. https:\/\/doi.org\/10.1109\/IROS51168.2021.9636655","DOI":"10.1109\/IROS51168.2021.9636655"},{"key":"8461_CR41","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103507","volume":"124","author":"Q Li","year":"2023","unstructured":"Li Q, Zhuang Y, Huai J (2023) Multi-sensor fusion for robust localization with moving object segmentation in complex dynamic 3D scenes. Int J Appl Earth Obs Geoinf 124:103507. https:\/\/doi.org\/10.1016\/j.jag.2023.103507","journal-title":"Int J Appl Earth Obs Geoinf"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-026-08461-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-026-08461-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-026-08461-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T10:34:53Z","timestamp":1774694093000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-026-08461-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,28]]},"references-count":41,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["8461"],"URL":"https:\/\/doi.org\/10.1007\/s11227-026-08461-1","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,28]]},"assertion":[{"value":"12 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 March 2026","order":3,"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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"306"}}