{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:42:38Z","timestamp":1771699358290,"version":"3.50.1"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726453","type":"print"},{"value":"9783031726460","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"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\/978-3-031-72646-0_12","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T08:45:29Z","timestamp":1730105129000},"page":"201-217","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["ProDepth: Boosting Self-supervised Multi-frame Monocular Depth with\u00a0Probabilistic Fusion"],"prefix":"10.1007","author":[{"given":"Sungmin","family":"Woo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wonjoon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Woo Jin","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dogyoon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangyoun","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Bangunharcana, A., Magd, A., Kim, K.S.: DualRefine: self-supervised depth and pose estimation through iterative Epipolar sampling and refinement toward equilibrium. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 726\u2013738 (2023)","DOI":"10.1109\/CVPR52729.2023.00077"},{"key":"12_CR2","unstructured":"Bian, J., et al.: Unsupervised scale-consistent depth and ego-motion learning from monocular video. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Casser, V., Pirk, S., Mahjourian, R., Angelova, A.: Depth prediction without the sensors: leveraging structure for unsupervised learning from monocular videos. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 8001\u20138008 (2019)","DOI":"10.1609\/aaai.v33i01.33018001"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Casser, V., Pirk, S., Mahjourian, R., Angelova, A.: Unsupervised monocular depth and ego-motion learning with structure and semantics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00051"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Schmid, C., Sminchisescu, C.: Self-supervised learning with geometric constraints in monocular video: connecting flow, depth, and camera. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7063\u20137072 (2019)","DOI":"10.1109\/ICCV.2019.00716"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"12_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, pp. 2650\u20132658 (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"12_CR8","doi-asserted-by":"publisher","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.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13692. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_14","DOI":"10.1007\/978-3-031-19824-3_14"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K., Tao, D.: Deep ordinal regression network for monocular depth estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2002\u20132011 (2018)","DOI":"10.1109\/CVPR.2018.00214"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"12_CR11","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, pp. 270\u2013279 (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"12_CR12","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, pp. 3828\u20133838 (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Gordon, A., Li, H., Jonschkowski, R., Angelova, A.: Depth from videos in the wild: unsupervised monocular depth learning from unknown cameras. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8977\u20138986 (2019)","DOI":"10.1109\/ICCV.2019.00907"},{"key":"12_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 (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Ambru\u015f, R., Chen, D., Zakharov, S., Gaidon, A.: Multi-frame self-supervised depth with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 160\u2013170 (2022)","DOI":"10.1109\/CVPR52688.2022.00026"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Hou, R., Li, J., Ambrus, R., Gaidon, A.: Semantically-guided representation learning for self-supervised monocular depth. In: ICLR (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Johnston, A., Carneiro, G.: Self-supervised monocular trained depth estimation using self-attention and discrete disparity volume. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00481"},{"key":"12_CR18","unstructured":"Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"12_CR19","doi-asserted-by":"publisher","unstructured":"Klingner, M., Term\u00f6hlen, J.A., Mikolajczyk, J., Fingscheidt, T.: Self-supervised monocular depth estimation: solving the dynamic object problem by semantic guidance. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds.) Computer Vision \u2013 ECCV 2020. ECCV 2020. LNCS, vol. 12365, pp. 582\u2013600. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_35","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Klodt, M., Vedaldi, A.: Supervising the new with the old: learning SFM from SFM. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 698\u2013713 (2018)","DOI":"10.1007\/978-3-030-01249-6_43"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Lee, S., Im, S., Lin, S., Kweon, I.S.: Learning monocular depth in dynamic scenes via instance-aware projection consistency. In: 35th AAAI Conference on Artificial Intelligence\/33rd Conference on Innovative Applications of Artificial Intelligence\/11th Symposium on Educational Advances in Artificial Intelligence, pp. 1863\u20131872. The Association for the Advancement of Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v35i3.16281"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Lee, S., Rameau, F., Pan, F., Kweon, I.S.: Attentive and contrastive learning for joint depth and motion field estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4862\u20134871 (2021)","DOI":"10.1109\/ICCV48922.2021.00482"},{"key":"12_CR23","unstructured":"Li, H., Gordon, A., Zhao, H., Casser, V., Angelova, A.: Unsupervised monocular depth learning in dynamic scenes. In: CoRL (2020)"},{"key":"12_CR24","unstructured":"Li, H., Gordon, A., Zhao, H., Casser, V., Angelova, A.: Unsupervised monocular depth learning in dynamic scenes. In: Conference on Robot Learning, pp. 1908\u20131917. PMLR (2021)"},{"key":"12_CR25","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21539\u201321548 (2023)","DOI":"10.1109\/CVPR52729.2023.02063"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Lyu, X., et al.: HR-Depth: high resolution self-supervised monocular depth estimation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 2294\u20132301 (2021)","DOI":"10.1609\/aaai.v35i3.16329"},{"issue":"5","key":"12_CR27","doi-asserted-by":"publisher","first-page":"1551","DOI":"10.1007\/s11263-021-01445-z","volume":"129","author":"R Mohan","year":"2021","unstructured":"Mohan, R., Valada, A.: EfficientPS: efficient panoptic segmentation. Int. J. Comput. Vision 129(5), 1551\u20131579 (2021)","journal-title":"Int. J. Comput. Vision"},{"issue":"4","key":"12_CR28","doi-asserted-by":"publisher","first-page":"6813","DOI":"10.1109\/LRA.2020.3017478","volume":"5","author":"V Patil","year":"2020","unstructured":"Patil, V., Van Gansbeke, W., Dai, D., Van Gool, L.: Don\u2019t forget the past: recurrent depth estimation from monocular video. IEEE Robot. Autom. Lett. 5(4), 6813\u20136820 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Pilzer, A., Xu, D., Puscas, M.M., Ricci, E., Sebe, N.: Unsupervised adversarial depth estimation using cycled generative networks. In: 3DV (2018)","DOI":"10.1109\/3DV.2018.00073"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Poggi, M., Aleotti, F., Tosi, F., Mattoccia, S.: On the uncertainty of self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3227\u20133237 (2020)","DOI":"10.1109\/CVPR42600.2020.00329"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Ranjan, A., Jampani, V., Kim, K., Sun, D., Wulff, J., Black, M.J.: Competitive collaboration: joint unsupervised learning of depth, camera motion, optical flow and motion segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01252"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Ruhkamp, P., Gao, D., Chen, H., Navab, N., Busam, B.: Attention meets geometry: geometry guided spatial-temporal attention for consistent self-supervised monocular depth estimation. In: 2021 International Conference on 3D Vision (3DV), pp. 837\u2013847. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00092"},{"key":"12_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1007\/978-3-030-58529-7_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Shu","year":"2020","unstructured":"Shu, C., Yu, K., Duan, Z., Yang, K.: Feature-metric loss for self-supervised learning of depth and Egomotion. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 572\u2013588. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_34"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Sun, P., et\u00a0al.: Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2446\u20132454 (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"12_CR35","unstructured":"Vijayanarasimhan, S., Ricco, S., Schmid, C., Sukthankar, R., Fragkiadaki, K.: SfM-Net: learning of structure and motion from video. arXiv preprint arXiv:1704.07804 (2017)"},{"key":"12_CR36","unstructured":"Wang, J., Zhang, G., Wu, Z., Li, X., Liu, L.: Self-supervised joint learning framework of depth estimation via implicit cues. arXiv:2006.09876 (2020)"},{"issue":"4","key":"12_CR37","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":"12_CR38","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1164\u20131174 (2021)","DOI":"10.1109\/CVPR46437.2021.00122"},{"key":"12_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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6112\u20136122 (2021)","DOI":"10.1109\/CVPR46437.2021.00605"},{"key":"12_CR40","doi-asserted-by":"crossref","unstructured":"Yin, Z., Shi, J.: GeoNet: unsupervised learning of dense depth, optical flow and camera pose. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00212"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Zhan, H., Garg, R., Weerasekera, C.S., Li, K., Agarwal, H., Reid, I.: Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00043"},{"key":"12_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, pp. 18537\u201318546 (2023)","DOI":"10.1109\/CVPR52729.2023.01778"},{"key":"12_CR43","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.: Unsupervised learning of depth and ego-motion from video. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.700"}],"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\/978-3-031-72646-0_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T08:50:42Z","timestamp":1730105442000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72646-0_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"ISBN":["9783031726453","9783031726460"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72646-0_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"28 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"}}]}}