{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T19:40:10Z","timestamp":1745696410680,"version":"3.40.4"},"publisher-location":"Singapore","reference-count":44,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819658145","type":"print"},{"value":"9789819658152","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\/978-981-96-5815-2_1","type":"book-chapter","created":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T19:13:45Z","timestamp":1745694825000},"page":"3-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DepthFisheye: Efficient Fine-Tuning of\u00a0Depth Estimation Models for\u00a0Fisheye Cameras"],"prefix":"10.1007","author":[{"given":"Wenbin","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhizhong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,26]]},"reference":[{"key":"1_CR1","unstructured":"Bhat, S.F., Alhashim, I., Wonka, P.: AdaBins: depth estimation using adaptive bins. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4009\u20134018 (2021)"},{"key":"1_CR2","unstructured":"Birkl, R., Wofk, D., M\u00fcller, M.: MiDaS v3.1 \u2013 a model zoo for robust monocular relative depth estimation (2023). https:\/\/arxiv.org\/abs\/2307.14460"},{"key":"1_CR3","first-page":"16664","volume":"35","author":"S Chen","year":"2022","unstructured":"Chen, S., et al.: AdaptFormer: adapting vision transformers for scalable visual recognition. Adv. Neural. Inf. Process. Syst. 35, 16664\u201316678 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Cui, Z., Heng, L., Yeo, Y.C., Geiger, A., Pollefeys, M., Sattler, T.: Real-time dense mapping for self-driving vehicles using fisheye cameras. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 6087\u20136093. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8793884"},{"issue":"1","key":"1_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/ima.1850050102","volume":"5","author":"KM Dawson-Howe","year":"1994","unstructured":"Dawson-Howe, K.M., Vernon, D.: Simple pinhole camera calibration. Int. J. Imaging Syst. Technol. 5(1), 1\u20136 (1994)","journal-title":"Int. J. Imaging Syst. Technol."},{"key":"1_CR6","unstructured":"Griffiths, R., Dansereau, D.G.: Adapting CNNs for fisheye cameras without retraining. arXiv preprint arXiv:2404.08187 (2024)"},{"key":"1_CR7","unstructured":"Gu, J., Chen, S., Wang, Z., Zhang, Y., Gong, P.: SARA: singular-value based adaptive low-rank adaption. arXiv preprint arXiv:2408.03290 (2024)"},{"key":"1_CR8","unstructured":"Han, Z., Gao, C., Liu, J., Zhang, S.Q., et\u00a0al.: Parameter-efficient fine-tuning for large models: a comprehensive survey. arXiv preprint arXiv:2403.14608 (2024)"},{"key":"1_CR9","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"1_CR10","unstructured":"Hu, M., et al.: Metric3Dv2: a versatile monocular geometric foundation model for zero-shot metric depth and surface normal estimation. arXiv preprint arXiv:2404.15506 (2024)"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Jia, M., et al.: Visual prompt tuning. In: European Conference on Computer Vision, pp. 709\u2013727. Springer (2022)","DOI":"10.1007\/978-3-031-19827-4_41"},{"issue":"8","key":"1_CR12","doi-asserted-by":"publisher","first-page":"1335","DOI":"10.1109\/TPAMI.2006.153","volume":"28","author":"J Kannala","year":"2006","unstructured":"Kannala, J., Brandt, S.S.: A generic camera model and calibration method for conventional, wide-angle, and fish-eye lenses. IEEE Trans. Pattern Anal. Mach. Intell. 28(8), 1335\u20131340 (2006)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Kumar, V.R., et al.: FisheyeDistanceNet: self-supervised scale-aware distance estimation using monocular fisheye camera for autonomous driving. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 574\u2013581. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9197319"},{"issue":"8","key":"1_CR14","doi-asserted-by":"publisher","first-page":"10252","DOI":"10.1109\/TITS.2021.3088950","volume":"23","author":"VR Kumar","year":"2021","unstructured":"Kumar, V.R., et al.: SVDistNet: self-supervised near-field distance estimation on surround view fisheye cameras. IEEE Trans. Intell. Transp. Syst. 23(8), 10252\u201310261 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Kumar, V.R., Klingner, M., Yogamani, S., Milz, S., Fingscheidt, T., Mader, P.: SynDistNet: self-supervised monocular fisheye camera distance estimation synergized with semantic segmentation for autonomous driving. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 61\u201371 (2021)","DOI":"10.1109\/WACV48630.2021.00011"},{"key":"1_CR16","unstructured":"Kumar, V.R., et al.: Near-field depth estimation using monocular fisheye camera: a semi-supervised learning approach using sparse lidar data. In: CVPR Workshop, vol.\u00a07, p.\u00a02 (2018)"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Kumar, V.R., Yogamani, S., Bach, M., Witt, C., Milz, S., M\u00e4der, P.: UnRectDepthNet: self-supervised monocular depth estimation using a generic framework for handling common camera distortion models. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 8177\u20138183. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9340732"},{"issue":"2","key":"1_CR18","doi-asserted-by":"publisher","first-page":"2830","DOI":"10.1109\/LRA.2021.3062324","volume":"6","author":"VR Kumar","year":"2021","unstructured":"Kumar, V.R., et al.: OmniDet: surround view cameras based multi-task visual perception network for autonomous driving. IEEE Robot. Autom. Lett. 6(2), 2830\u20132837 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Kundu, J.N., Uppala, P.K., Pahuja, A., Babu, R.V.: AdaDepth: unsupervised content congruent adaptation for depth estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2656\u20132665 (2018)","DOI":"10.1109\/CVPR.2018.00281"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Lee, J., Park, D., Lee, D., Ji, D.: Semi-supervised 360 depth estimation from multiple fisheye cameras with pixel-level selective loss. In: 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2022, pp. 2290\u20132294. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9746232"},{"key":"1_CR21","unstructured":"Lee, J.H., Han, M.K., Ko, D.W., Suh, I.H.: From big to small: multi-scale local planar guidance for monocular depth estimation. arXiv preprint arXiv:1907.10326 (2019)"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Lee, J., et al.: SlaBins: fisheye depth estimation using slanted bins on road environments. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8765\u20138774 (2023)","DOI":"10.1109\/ICCV51070.2023.00805"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: LORS: low-rank residual structure for parameter-efficient network stacking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15866\u201315876 (2024)","DOI":"10.1109\/CVPR52733.2024.01502"},{"issue":"12","key":"1_CR24","doi-asserted-by":"publisher","first-page":"9904","DOI":"10.1109\/TPAMI.2021.3132068","volume":"44","author":"Z Li","year":"2021","unstructured":"Li, Z., Sun, Y., Zhang, L., Tang, J.: CTNet: context-based tandem network for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 9904\u20139917 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"9","key":"1_CR25","doi-asserted-by":"publisher","first-page":"2070","DOI":"10.1109\/TPAMI.2018.2852750","volume":"41","author":"Z Li","year":"2018","unstructured":"Li, Z., Tang, J., Mei, T.: Deep collaborative embedding for social image understanding. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2070\u20132083 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"1_CR26","doi-asserted-by":"publisher","first-page":"3292","DOI":"10.1109\/TPAMI.2022.3179507","volume":"45","author":"Y Liao","year":"2022","unstructured":"Liao, Y., Xie, J., Geiger, A.: KITTI-360: a novel dataset and benchmarks for urban scene understanding in 2D and 3D. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3292\u20133310 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR27","unstructured":"Liu, T., et al.: Sparse-tuning: adapting vision transformers with efficient fine-tuning and inference. arXiv preprint arXiv:2405.14700 (2024)"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Maximov, M., Galim, K., Leal-Taix\u00e9, L.: Focus on defocus: bridging the synthetic to real domain gap for depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1071\u20131080 (2020)","DOI":"10.1109\/CVPR42600.2020.00115"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Patil, V., Sakaridis, C., Liniger, A., Van\u00a0Gool, L.: P3Depth: monocular depth estimation with a piecewise planarity prior. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1610\u20131621 (2022)","DOI":"10.1109\/CVPR52688.2022.00166"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Plaut, E., Ben\u00a0Yaacov, E., El\u00a0Shlomo, B.: 3D object detection from a single fisheye image without a single fisheye training image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3659\u20133667 (2021)","DOI":"10.1109\/CVPRW53098.2021.00405"},{"issue":"3","key":"1_CR31","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","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 Trans. Pattern Anal. Mach. Intell. 44(3), 1623\u20131637 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Rey-Area, M., Yuan, M., Richardt, C.: 360MonoDepth: high-resolution 360deg monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3762\u20133772 (2022)","DOI":"10.1109\/CVPR52688.2022.00374"},{"issue":"3","key":"1_CR33","doi-asserted-by":"publisher","first-page":"8502","DOI":"10.1109\/LRA.2022.3188106","volume":"7","author":"AR Sekkat","year":"2022","unstructured":"Sekkat, A.R., et al.: SynWoodScape: synthetic surround-view fisheye camera dataset for autonomous driving. IEEE Robot. Autom. Lett. 7(3), 8502\u20138509 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"24","key":"1_CR34","doi-asserted-by":"publisher","first-page":"9866","DOI":"10.3390\/s23249866","volume":"23","author":"E Son","year":"2023","unstructured":"Son, E., Choi, J., Song, J., Jin, Y., Lee, S.J.: Monocular depth estimation from a fisheye camera based on knowledge distillation. Sensors 23(24), 9866 (2023)","journal-title":"Sensors"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Tosi, F., Ramirez, P.Z., Poggi, M.: Diffusion models for monocular depth estimation: overcoming challenging conditions. arXiv preprint arXiv:2407.16698 (2024)","DOI":"10.1007\/978-3-031-73337-6_14"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Wei, Z., et al.: Stronger fewer & superior: harnessing vision foundation models for domain generalized semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 28619\u201328630 (2024)","DOI":"10.1109\/CVPR52733.2024.02704"},{"key":"1_CR37","unstructured":"Xin, Y., et al.: Parameter-efficient fine-tuning for pre-trained vision models: a survey. arXiv preprint arXiv:2402.02242 (2024)"},{"key":"1_CR38","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, pp. 10371\u201310381 (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Yin, W., et al.: Metric3D: towards zero-shot metric 3D prediction from a single image. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9043\u20139053 (2023)","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"1_CR40","unstructured":"Zaken, E.B., Ravfogel, S., Goldberg, Y.: BitFit: simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199 (2021)"},{"key":"1_CR41","unstructured":"Zhang, C., Zhang, C., Zhang, M., Kweon, I.S.: Text-to-image diffusion models in generative AI: a survey. arXiv preprint arXiv:2303.07909 (2023)"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"1_CR43","unstructured":"Zhu, R., Wang, C., Song, Z., Liu, L., Zhang, T., Zhang, Y.: ScaleDepth: decomposing metric depth estimation into scale prediction and relative depth estimation. arXiv preprint arXiv:2407.08187 (2024)"},{"issue":"35","key":"1_CR44","doi-asserted-by":"publisher","first-page":"1298","DOI":"10.21105\/joss.01298","volume":"4","author":"A Zonca","year":"2019","unstructured":"Zonca, A., et al.: healpy: equal area pixelization and spherical harmonics transforms for data on the sphere in Python. J. Open Source Softw. 4(35), 1298 (2019)","journal-title":"J. Open Source Softw."}],"container-title":["Lecture Notes in Computer Science","Computational Visual Media"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-5815-2_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T19:13:58Z","timestamp":1745694838000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-5815-2_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819658145","9789819658152"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-5815-2_1","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":"26 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Visual Media","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong SAR","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iccvm.org\/2025\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}