{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:01:36Z","timestamp":1786978896861,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729720","type":"print"},{"value":"9783031729737","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-72973-7_10","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T10:03:04Z","timestamp":1730368984000},"page":"162-178","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Resolving Scale Ambiguity in\u00a0Multi-view 3D Reconstruction Using Dual-Pixel Sensors"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1444-2721","authenticated-orcid":false,"given":"Kohei","family":"Ashida","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2891-5993","authenticated-orcid":false,"given":"Hiroaki","family":"Santo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7595-1300","authenticated-orcid":false,"given":"Fumio","family":"Okura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1935-4752","authenticated-orcid":false,"given":"Yasuyuki","family":"Matsushita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Abuolaim, A., Afifi, M., Brown, M.S.: Improving single-image defocus deblurring: how dual-pixel images help through multi-task learning. In: IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 82\u201390 (2022)","DOI":"10.1109\/WACV51458.2022.00016"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Abuolaim, A., Brown, M.S.: Defocus deblurring using dual-pixel data. In: Proceedings of European Conference on Computer Vision (ECCV), pp. 111\u2013126 (2020)","DOI":"10.1007\/978-3-030-58607-2_7"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Abuolaim, A., Delbracio, M., Kelly, D., Brown, M.S., Milanfar, P.: Learning to reduce defocus blur by realistically modeling dual-pixel data. In: Proceedings of IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2289\u20132298 (2021)","DOI":"10.1109\/ICCV48922.2021.00229"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Abuolaim, A., Punnappurath, A., Brown, M.S.: Revisiting autofocus for smartphone cameras. In: Proceedings of European Conference on Computer Vision (ECCV), pp. 545\u2013559 (2018)","DOI":"10.1007\/978-3-030-01267-0_32"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Abuolaim, A., Timofte, R., Brown, M.S.: NTIRE 2021 challenge for defocus deblurring using dual-pixel images: methods and results. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 578\u2013587 (2021)","DOI":"10.1109\/CVPRW53098.2021.00070"},{"key":"10_CR6","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":"10_CR7","doi-asserted-by":"crossref","unstructured":"Engel, J., St\u00fcckler, J., Cremers, D.: Large-scale direct SLAM with stereo cameras. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1935\u20131942 (2015)","DOI":"10.1109\/IROS.2015.7353631"},{"issue":"6","key":"10_CR8","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"MA Fischler","year":"1981","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381\u2013395 (1981)","journal-title":"Commun. ACM"},{"issue":"3","key":"10_CR9","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1109\/TRO.2018.2820722","volume":"34","author":"D Frost","year":"2018","unstructured":"Frost, D., Prisacariu, V., Murray, D.: Recovering stable scale in monocular SLAM using object-supplemented bundle adjustment. IEEE Trans. Rob. 34(3), 736\u2013747 (2018)","journal-title":"IEEE Trans. Rob."},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Garg, R., Wadhwa, N., Ansari, S., Barron, J.T.: Learning single camera depth estimation using dual-pixels. In: Proceedings of IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7628\u20137637 (2019)","DOI":"10.1109\/ICCV.2019.00772"},{"key":"10_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-70873-7","volume-title":"Matrix Albegra","author":"J Gentle","year":"2007","unstructured":"Gentle, J.: Matrix Albegra. Springer Texts in Statistics, Springer, New York (2007)"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Giubilato, R., Chiodini, S., Pertile, M., Debei, S.: Scale correct monocular visual odometry using a lidar altimeter. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3694\u20133700 (2018)","DOI":"10.1109\/IROS.2018.8594096"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Herrmann, C., et al.: Learning to autofocus. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2227\u20132236 (2020)","DOI":"10.1109\/CVPR42600.2020.00230"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Jung, S.H., Heo, Y.S.: Disparity probability volume guided defocus deblurring using dual pixel data. In: Proceedings of International Conference on Information and Communication Technology Convergence (ICTC), pp. 305\u2013308 (2021)","DOI":"10.1109\/ICTC52510.2021.9621024"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Kang, M., Choe, J., Ha, H., Jeon, H.G., Im, S., Kweon, I.S.: Facial depth and normal estimation using single dual-pixel camera. In: Proceedings of European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-20074-8_11"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Kashiwagi, M., Mishima, N., Kozakaya, T., Hiura, S.: Deep depth from aberration map. In: Proceedings of IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00417"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Kim, D., Jang, H., Kim, I., Kim, M.H.: Spatio-focal bidirectional disparity estimation from a dual-pixel image. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5023\u20135032 (2023)","DOI":"10.1109\/CVPR52729.2023.00486"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Knorr, S.B., Kurz, D.: Leveraging the user\u2019s face for absolute scale estimation in handheld monocular SLAM. In: Proceedings of IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 11\u201317 (2016)","DOI":"10.1109\/ISMAR.2016.20"},{"issue":"2","key":"10_CR19","doi-asserted-by":"publisher","first-page":"780","DOI":"10.1109\/LRA.2018.2789841","volume":"3","author":"SH Lee","year":"2018","unstructured":"Lee, S.H., de Croon, G.: Stability-based scale estimation for monocular SLAM. IEEE Robot. Autom. Lett. 3(2), 780\u2013787 (2018)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Li, F., Guo, H., Santo, H., Okura, F., Matsushita, Y.: Learning to synthesize photorealistic dual-pixel images from RGBD frames. In: International Conference on Computational Photography (ICCP), pp. 1\u201311 (2023)","DOI":"10.1109\/ICCP56744.2023.10233839"},{"key":"10_CR21","unstructured":"Mishima, N., Seki, A., Hiura, S.: Absolute scale from varifocal monocular camera through SfM and defocus combined. In: Proceedings of British Machine Vision Conference (BMVC) (2021)"},{"issue":"1\u20134","key":"10_CR22","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/s10846-010-9490-z","volume":"61","author":"G N\u00fctzi","year":"2011","unstructured":"N\u00fctzi, G., Weiss, S., Scaramuzza, D., Siegwart, R.: Fusion of IMU and vision for absolute scale estimation in monocular SLAM. J. Intell. Robot. Syst. 61(1\u20134), 287\u2013299 (2011)","journal-title":"J. Intell. Robot. Syst."},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Pan, L., Chowdhury, S., Hartley, R., Liu, M., Zhang, H., Li, H.: Dual pixel exploration: Simultaneous depth estimation and image restoration. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4340\u20134349 (2021)","DOI":"10.1109\/CVPR46437.2021.00432"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Punnappurath, A., Abuolaim, A., Afifi, M., Brown, M.S.: Modeling defocus-disparity in dual-pixel sensors. In: International Conference on Computational Photography (ICCP), pp. 1\u201312 (2020)","DOI":"10.1109\/ICCP48838.2020.9105278"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Punnappurath, A., Brown, M.S.: Reflection removal using a dual-pixel sensor. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1556\u20131565 (2019)","DOI":"10.1109\/CVPR.2019.00165"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Roussel, T., Van\u00a0Eycken, L., Tuytelaars, T.: Monocular depth estimation in new environments with absolute scale. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1735\u20131741 (2019)","DOI":"10.1109\/IROS40897.2019.8967677"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Rukhovich, D., Mouritzen, D., Kaestner, R., Rufli, M., Velizhev, A.: Estimation of absolute scale in monocular SLAM using synthetic data. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 803\u2013812 (2019)","DOI":"10.1109\/ICCVW.2019.00108"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Scaramuzza, D., Fraundorfer, F., Pollefeys, M., Siegwart, R.: Absolute scale in structure from motion from a single vehicle mounted camera by exploiting nonholonomic constraints. In: Proceedings of IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1413\u20131419 (2009)","DOI":"10.1109\/ICCV.2009.5459294"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Shibata, A., Fujii, H., Yamashita, A., Asama, H.: Absolute scale structure from motion using a refractive plate. In: Proceedings of IEEE\/SICE International Symposium on System Integration (SII), pp. 540\u2013545 (2015)","DOI":"10.1109\/SII.2015.7405037"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Shibata, A., Fujii, H., Yamashita, A., Asama, H.: Scale-reconstructable structure from motion using refraction with a single camera. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 5239\u20135244 (2015)","DOI":"10.1109\/ICRA.2015.7139929"},{"issue":"1","key":"10_CR31","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1109\/LRA.2017.2772330","volume":"3","author":"T Shiozaki","year":"2017","unstructured":"Shiozaki, T., Dissanayake, G.: Eliminating scale drift in monocular SLAM using depth from defocus. IEEE Robot. Autom. Lett. 3(1), 581\u2013587 (2017)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Song, S., Chandraker, M.: Robust scale estimation in real-time monocular sfm for autonomous driving. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1566\u20131573 (2014)","DOI":"10.1109\/CVPR.2014.203"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Sucar, E., Hayet, J.B.: Bayesian scale estimation for monocular SLAM based on generic object detection for correcting scale drift. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 5152\u20135158 (2018)","DOI":"10.1109\/ICRA.2018.8461178"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Sumikura, S., Sakurada, K., Kawaguchi, N., Nakamura, R.: Scale estimation of monocular SfM for a multi-modal stereo camera. In: Proceedings of Asian Conference on Computer Vision (ACCV), pp. 281\u2013297 (2019)","DOI":"10.1007\/978-3-030-20893-6_18"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Wadhwa, N., et al.: Synthetic depth-of-field with a single-camera mobile phone. In: ACM Transactions on Graphics (TOG), pp. 1\u201313 (2018)","DOI":"10.1145\/3197517.3201329"},{"issue":"6","key":"10_CR36","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1016\/j.isprsjprs.2009.03.004","volume":"64","author":"C W\u00f6hler","year":"2009","unstructured":"W\u00f6hler, C., d\u2019Angelo, P., Kr\u00fcger, L., Kuhl, A., Gro\u00df, H.M.: Monocular 3D scene reconstruction at absolute scale. ISPRS J. Photogramm. Remote. Sens. 64(6), 529\u2013540 (2009)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Xin, S., et al.: Defocus map estimation and deblurring from a single dual-pixel image. In: Proceedings of IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2228\u20132238 (2021)","DOI":"10.1109\/ICCV48922.2021.00223"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Yang, Y., Pan, L., Liu, L., Liu, M.: K3DN: Disparity-aware kernel estimation for dual-pixel defocus deblurring. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13263\u201313272 (2023)","DOI":"10.1109\/CVPR52729.2023.01274"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhang, J., Tao, D.: Towards scale-aware, robust, and generalizable unsupervised monocular depth estimation by integrating IMU motion dynamics. In: Proceedings of European Conference on Computer Vision (ECCV), pp. 143\u2013160 (2022)","DOI":"10.1007\/978-3-031-19839-7_9"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wadhwa, N., Orts-Escolano, S., H\u00e4ne, C., Fanello, S.R., Garg, R.: Du2Net: Learning depth estimation from dual-cameras and dual-pixels. In: Proceedings of European Conference on Computer Vision (ECCV), pp. 582\u2013598 (2020)","DOI":"10.1007\/978-3-030-58452-8_34"},{"key":"10_CR41","unstructured":"Zhou, D., Dai, Y., Li, H.: Reliable scale estimation and correction for monocular visual odometry. In: Proceedings of IEEE Intelligent Vehicles Symposium (IV), pp. 490\u2013495 (2016)"},{"issue":"2","key":"10_CR42","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1109\/TITS.2019.2900330","volume":"21","author":"D Zhou","year":"2019","unstructured":"Zhou, D., Dai, Y., Li, H.: Ground-plane-based absolute scale estimation for monocular visual odometry. IEEE Trans. Intell. Transp. Syst. 21(2), 791\u2013802 (2019)","journal-title":"IEEE Trans. Intell. Transp. Syst."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72973-7_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:27:00Z","timestamp":1737098820000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72973-7_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031729720","9783031729737"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72973-7_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","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"}}]}}