{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T16:16:45Z","timestamp":1774541805779,"version":"3.50.1"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031923869","type":"print"},{"value":"9783031923876","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-92387-6_18","type":"book-chapter","created":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T18:42:50Z","timestamp":1748198570000},"page":"235-251","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["NimbleD: Enhancing Self-supervised Monocular Depth Estimation with\u00a0Pseudo-labels and\u00a0Large-Scale Video Pre-training"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7243-9808","authenticated-orcid":false,"given":"Albert","family":"Luginov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9394-343X","authenticated-orcid":false,"given":"Muhammad","family":"Shahzad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"18_CR1","unstructured":"Bhat, S.F., Birkl, R., Wofk, D., Wonka, P., M\u00fcller, M.: ZoeDepth: zero-shot transfer by combining relative and metric depth. arXiv preprint arXiv:2302.12288 (2023)"},{"key":"18_CR2","unstructured":"Birkl, R., Wofk, D., M\u00fcller, M.: MiDaS v3.1 - a model zoo for robust monocular relative depth estimation. arXiv preprint arXiv:2307.14460 (2023)"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Choi, S., Choi, D., Kim, D.: TIE-KD: Teacher-independent and explainable knowledge distillation for monocular depth estimation. Image Vis. Comput. (2024)","DOI":"10.1016\/j.imavis.2024.105110"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Dong, Y.J., Zhang, F.L., Zhang, S.H.: MAL: motion-aware loss with temporal and distillation hints for self-supervised depth estimation. In: IEEE International Conference on Robotics and Automation (ICRA) (2024)","DOI":"10.1109\/ICRA57147.2024.10610688"},{"key":"18_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\,\\times \\,$$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"18_CR8","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Advances in Neural Information Processing Systems (2014)"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Gao, W., Rao, D., Yang, Y., Chen, J.: Edge devices friendly self-supervised monocular depth estimation via knowledge distillation. IEEE Robot. Autom. Lett. (2023)","DOI":"10.1109\/LRA.2023.3330054"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Garg, R., Bg, V.K., Carneiro, G., Reid, I.: Unsupervised CNN for single view depth estimation: geometry to the rescue. In: European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. (IJRR) (2013)","DOI":"10.1177\/0278364913491297"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac\u00a0Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac\u00a0Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Vasiljevic, I., Chen, D., Ambrus, R., Gaidon, A.: Towards zero-shot scale-aware monocular depth estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00847"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Han, W., Yin, J., Shen, J.: Self-supervised monocular depth estimation by direction-aware cumulative convolution network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00791"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR17","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: Advances in Neural Information Processing Systems (2015)"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Ke, B., Obukhov, A., Huang, S., Metzger, N., Daudt, R.C., Schindler, K.: Repurposing diffusion-based image generators for monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, K., Liu, C., Qin, Z., Luo, Z., Wang, J.: Structured knowledge distillation for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00271"},{"key":"18_CR20","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: International Conference on Learning Representations (2017)"},{"key":"18_CR21","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Luginov, A., Makarov, I.: SwiftDepth: an efficient hybrid CNN-transformer model for self-supervised monocular depth estimation on mobile devices. In: 2023 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct) (2023)","DOI":"10.1109\/ISMAR-Adjunct60411.2023.00137"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Moon, J., Bello, J.L.G., Kwon, B., Kim, M.: From-ground-to-objects: coarse-to-fine self-supervised monocular depth estimation of dynamic objects with ground contact prior. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01001"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Piccinelli, L., et al.: UniDepth: universal monocular metric depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"18_CR25","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning (2021)"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Saxena, A., Sun, M., Ng, A.Y.: Make3D: learning 3D scene structure from a single still image. IEEE Trans. Pattern Anal. Mach. Intell. (2009)","DOI":"10.1109\/TPAMI.2008.132"},{"key":"18_CR30","unstructured":"Saxena, S., Hur, J., Herrmann, C., Sun, D., Fleet, D.J.: Zero-shot metric depth with a field-of-view conditioned diffusion model. arXiv preprint arXiv:2312.13252 (2023)"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Shaker, A., Maaz, M., Rasheed, H., Khan, S., Yang, M.H., Khan, F.S.: SwiftFormer: efficient additive attention for transformer-based real-time mobile vision applications. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01598"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: European Conference on Computer Vision (ECCV) (2012)","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"18_CR33","unstructured":"Spencer, J., Russell, C., Hadfield, S., Bowden, R.: Deconstructing self-supervised monocular reconstruction: the design decisions that matter. Trans. Mach. Learn. Res. (2022)"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Spencer, J., Russell, C., Hadfield, S., Bowden, R.: Kick back & relax: learning to reconstruct the world by watching SlowTV. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01445"},{"key":"18_CR35","unstructured":"Spencer, J., et al.: The third monocular depth estimation challenge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2024)"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., Geiger, A.: sparsity invariant CNNs. In: 2017 International Conference on 3D Vision (3DV) (2017)","DOI":"10.1109\/3DV.2017.00012"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Y., Li, X., Shi, M., Xian, K., Cao, Z.: Knowledge distillation for fast and accurate monocular depth estimation on mobile devices. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2021)","DOI":"10.1109\/CVPRW53098.2021.00278"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Y., Liang, Y., Xu, H., Jiao, S., Yu, H.: SQLdepth: generalizable self-supervised fine-structured monocular depth estimation. In: Proceedings of the AAAI Conference on Artificial Intelligence (2024)","DOI":"10.1609\/aaai.v38i6.28383"},{"key":"18_CR39","unstructured":"Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. (2004)"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: CutMix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, N., Nex, F., Vosselman, G., Kerle, N.: Lite-mono: a lightweight CNN and transformer architecture for self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01778"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, C., et al.: GasMono: geometry-aided self-supervised monocular depth estimation for indoor scenes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01485"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.700"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-92387-6_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T18:43:07Z","timestamp":1748198587000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-92387-6_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031923869","9783031923876"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-92387-6_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}