{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:46:02Z","timestamp":1777567562857,"version":"3.51.4"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729515","type":"print"},{"value":"9783031729522","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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\/978-3-031-72952-2_16","type":"book-chapter","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T05:02:02Z","timestamp":1727672522000},"page":"269-285","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["M$$^2$$Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimation"],"prefix":"10.1007","author":[{"given":"Yingshuang","family":"Zou","sequence":"first","affiliation":[]},{"given":"Yikang","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Xi","family":"Qiu","sequence":"additional","affiliation":[]},{"given":"Haoqian","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Haotian","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,1]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Bae, G., Budvytis, I., Cipolla, R.: Multi-view depth estimation by fusing single-view depth probability with multi-view geometry. In: CVPR, pp. 2842\u20132851 (2022)","DOI":"10.1109\/CVPR52688.2022.00286"},{"key":"16_CR2","unstructured":"Bhat, S.F., Alhashim, I., Wonka, P.: AdaBins: depth estimation using adaptive bins. In: CVPR, pp. 4009\u20134018 (2021)"},{"key":"16_CR3","unstructured":"Bian, J., et al.: Unsupervised scale-consistent depth and ego-motion learning from monocular video. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Bui, N.T., Hoang, D.H., Tran, M.T., Le, N.: SAM3D: segment anything model in volumetric medical images. arXiv preprint arXiv:2309.03493 (2023)","DOI":"10.1109\/ISBI56570.2024.10635844"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: CVPR, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"16_CR6","unstructured":"Cheng, Y., et al.: Segment and track anything. arXiv preprint arXiv:2305.06558 (2023)"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Collins, R.T.: A space-sweep approach to true multi-image matching. In: Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 358\u2013363. IEEE (1996)","DOI":"10.1109\/CVPR.1996.517097"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Ding, Y., et al.: TransMVSNet: global context-aware multi-view stereo network with transformers. In: CVPR, pp. 8585\u20138594 (2022)","DOI":"10.1109\/CVPR52688.2022.00839"},{"key":"16_CR9","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, vol. 27 (2014)"},{"key":"16_CR10","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1007\/978-3-031-19824-3_14","volume-title":"ECCV 2022","author":"Z Feng","year":"2022","unstructured":"Feng, Z., Yang, L., Jing, L., Wang, H., Tian, Y., Li, B.: Disentangling object motion and occlusion for unsupervised multi-frame monocular depth. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13692, pp. 228\u2013244. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_14"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac\u00a0Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: CVPR, pp. 270\u2013279 (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth prediction. In: ICCV, pp. 3828\u20133838 (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Gu, X., Fan, Z., Zhu, S., Dai, Z., Tan, F., Tan, P.: Cascade cost volume for high-resolution multi-view stereo and stereo matching. In: CVPR, pp. 2495\u20132504 (2020)","DOI":"10.1109\/CVPR42600.2020.00257"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Ambrus, R., Pillai, S., Raventos, A., Gaidon, A.: 3D packing for self-supervised monocular depth estimation. In: CVPR, pp. 2485\u20132494 (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Ambrus, R., Chen, D., Zakharov, S., Gaidon, A.: Multi-frame self-supervised depth with transformers. In: CVPR, pp. 160\u2013170 (2022)","DOI":"10.1109\/CVPR52688.2022.00026"},{"issue":"2","key":"16_CR16","doi-asserted-by":"publisher","first-page":"5397","DOI":"10.1109\/LRA.2022.3150884","volume":"7","author":"V Guizilini","year":"2022","unstructured":"Guizilini, V., Vasiljevic, I., Ambrus, R., Shakhnarovich, G., Gaidon, A.: Full surround monodepth from multiple cameras. IEEE Robot. Autom. Lett. 7(2), 5397\u20135404 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Guo, X., Yang, K., Yang, W., Wang, X., Li, H.: Group-wise correlation stereo network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3273\u20133282 (2019)","DOI":"10.1109\/CVPR.2019.00339"},{"key":"16_CR18","unstructured":"He, H., Zhang, J., Xu, M., Liu, J., Du, B., Tao, D.: Scalable mask annotation for video text spotting. arXiv preprint arXiv:2305.01443 (2023)"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"He, J., Zhang, S., Yang, M., Shan, Y., Huang, T.: Bi-directional cascade network for perceptual edge detection. In: CVPR, pp. 3828\u20133837 (2019)","DOI":"10.1109\/CVPR.2019.00395"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"16_CR21","unstructured":"Kim, J.H., Hur, J., Nguyen, T.P., Jeong, S.G.: Self-supervised surround-view depth estimation with volumetric feature fusion. In: NeurIPS, pp. 4032\u20134045 (2022)"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: ICCV, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Li, R., et al.: Learning to fuse monocular and multi-view cues for multi-frame depth estimation in dynamic scenes. In: CVPR, pp. 21539\u201321548 (2023)","DOI":"10.1109\/CVPR52729.2023.02063"},{"key":"16_CR24","unstructured":"Li, Z., Wang, X., Liu, X., Jiang, J.: BinsFormer: revisiting adaptive bins for monocular depth estimation. arXiv preprint arXiv:2204.00987 (2022)"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Ma, J., Wang, B.: Segment anything in medical images. arXiv preprint arXiv:2304.12306 (2023)","DOI":"10.1038\/s41467-024-44824-z"},{"key":"16_CR28","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: International Conference on Machine Learning (ICML), pp. 807\u2013814 (2010)"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Schmied, A., Fischer, T., Danelljan, M., Pollefeys, M., Yu, F.: R3D3: dense 3D reconstruction of dynamic scenes from multiple cameras. In: ICCV, pp. 3216\u20133226 (2023)","DOI":"10.1109\/ICCV51070.2023.00298"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: CVPR, pp. 4104\u20134113 (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Shi, Y., Cai, H., Ansari, A., Porikli, F.: EGA-Depth: efficient guided attention for self-supervised multi-camera depth estimation. In: CVPRW, pp. 119\u2013129 (2023)","DOI":"10.1109\/CVPRW59228.2023.00017"},{"key":"16_CR32","unstructured":"Talker, L., Cohen, A., Yosef, E., Dana, A., Dinerstein, M.: Mind the edge: refining depth edges in sparsely-supervised monocular depth estimation. arXiv preprint arXiv:2212.05315 (2022)"},{"key":"16_CR33","unstructured":"Teed, Z., Deng, J.: DROID-SLAM: deep visual SLAM for monocular, stereo, and RGB-D cameras. In: Advances in Neural Information Processing Systems, vol. 34, pp. 16558\u201316569 (2021)"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Crafting monocular cues and velocity guidance for self-supervised multi-frame depth learning. In: AAAI, pp. 2689\u20132697 (2023)","DOI":"10.1609\/aaai.v37i3.25368"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Y., Liang, Y., Xu, H., Jiao, S., Yu, H.: SQLdepth: generalizable self-supervised fine-structured monocular depth estimation. arXiv preprint arXiv:2309.00526 (2023)","DOI":"10.1609\/aaai.v38i6.28383"},{"issue":"4","key":"16_CR36","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Watson, J., Mac\u00a0Aodha, O., Prisacariu, V., Brostow, G., Firman, M.: The temporal opportunist: self-supervised multi-frame monocular depth. In: CVPR, pp. 1164\u20131174 (2021)","DOI":"10.1109\/CVPR46437.2021.00122"},{"key":"16_CR38","unstructured":"Wei, Y., et al.: SurroundDepth: entangling surrounding views for self-supervised multi-camera depth estimation. In: Conference on Robot Learning (CoRL), pp. 539\u2013549 (2022)"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Wimbauer, F., Yang, N., Von\u00a0Stumberg, L., Zeller, N., Cremers, D.: MonoRec: semi-supervised dense reconstruction in dynamic environments from a single moving camera. In: CVPR, pp. 6112\u20136122 (2021)","DOI":"10.1109\/CVPR46437.2021.00605"},{"key":"16_CR40","unstructured":"Wu, J., Xu, R., Wood-Doughty, Z., Wang, C.: Segment anything model is a good teacher for local feature learning. arXiv preprint arXiv:2309.16992 (2023)"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Yang, N., Wang, R., Stuckler, J., Cremers, D.: Deep virtual stereo odometry: leveraging deep depth prediction for monocular direct sparse odometry. In: ECCV, pp. 817\u2013833 (2018)","DOI":"10.1007\/978-3-030-01237-3_50"},{"key":"16_CR42","unstructured":"Yu, T., et al.: Inpaint anything: segment anything meets image inpainting. arXiv preprint arXiv:2304.06790 (2023)"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Yuan, W., Gu, X., Dai, Z., Zhu, S., Tan, P.: New CRFs: neural window fully-connected CRFs for monocular depth estimation. arXiv preprint arXiv:2203.01502 (2022)","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"16_CR44","unstructured":"Zhang, C., et al.: Faster segment anything: towards lightweight SAM for mobile applications. arXiv preprint arXiv:2306.14289 (2023)"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, K., Liu, D.: Customized segment anything model for medical image segmentation. arXiv preprint arXiv:2304.13785 (2023)","DOI":"10.2139\/ssrn.4495221"},{"key":"16_CR46","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, pp. 18537\u201318546 (2023)","DOI":"10.1109\/CVPR52729.2023.01778"}],"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\/978-3-031-72952-2_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T05:11:21Z","timestamp":1727673081000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72952-2_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"ISBN":["9783031729515","9783031729522"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72952-2_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,1]]},"assertion":[{"value":"1 October 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"}}]}}