{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:23:02Z","timestamp":1778080982154,"version":"3.51.4"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198410","type":"print"},{"value":"9783031198427","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19842-7_8","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T12:12:59Z","timestamp":1666440779000},"page":"125-142","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["DevNet: Self-supervised Monocular Depth Learning via\u00a0Density Volume Construction"],"prefix":"10.1007","author":[{"given":"Kaichen","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lanqing","family":"Hong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changhao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoqiang","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyong","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenguo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"8_CR1","unstructured":"Bhat, S.F., Alhashim, I., Wonka, P.: AdaBins: depth estimation using adaptive bins. In: CVPR (2021)"},{"key":"8_CR2","unstructured":"Bian, J., et al.: Unsupervised scale-consistent depth and ego-motion learning from monocular video. In: NeurIPS (2019)"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Du, Y., Zhang, Y., Yu, H.X., Tenenbaum, J.B., Wu, J.: Neural radiance flow for 4D view synthesis and video processing. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01406"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"8_CR5","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. arXiv preprint arXiv:1406.2283 (2014)"},{"issue":"3","key":"8_CR6","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1109\/TPAMI.2017.2658577","volume":"40","author":"J Engel","year":"2017","unstructured":"Engel, J., Koltun, V., Cremers, D.: Direct sparse odometry. TPAMI 40(3), 611\u2013625 (2017)","journal-title":"TPAMI"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Engel, J., St\u00fcckler, J., Cremers, D.: Large-scale direct slam with stereo cameras. In: IROS (2015)","DOI":"10.1109\/IROS.2015.7353631"},{"key":"8_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-46484-8_45","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Garg","year":"2016","unstructured":"Garg, R., B.G., V.K., Carneiro, G., Reid, I.: Unsupervised CNN for single view depth estimation: geometry to the rescue. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 740\u2013756. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_45"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth estimation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"8_CR12","unstructured":"GonzalezBello, J.L., Kim, M.: Forget about the LiDAR: self-supervised depth estimators with med probability volumes. In: NeurIPS (2020)"},{"key":"8_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: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00907"},{"key":"8_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":"8_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"8_CR16","unstructured":"Huo, Y., et al.: Learning depth-guided convolutions for monocular 3D object detection. In: CVPR Workshop (2020)"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Ji, P., Li, R., Bhanu, B., Xu, Y.: MonoIndoor: towards good practice of self-supervised monocular depth estimation for indoor environments. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01255"},{"key":"8_CR18","unstructured":"Jin, H., Favaro, P., Soatto, S.: Real-time feature tracking and outlier rejection with changes in illumination. In: ICCV (2001)"},{"key":"8_CR19","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":"8_CR20","doi-asserted-by":"crossref","unstructured":"Kajiya, J.T.: The rendering equation. In: Annual Conference on Computer Graphics and Interactive Techniques (1986)","DOI":"10.1145\/15922.15902"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Kalia, M., Navab, N., Salcudean, T.: A real-time interactive augmented reality depth estimation technique for surgical robotics. In: ICRA (2019)","DOI":"10.1109\/ICRA.2019.8793610"},{"key":"8_CR22","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":"8_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., Ushiku, Y., Harada, T.: Pose graph optimization for unsupervised monocular visual odometry. In: ICRA (2019)","DOI":"10.1109\/ICRA.2019.8793706"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Li, Z., Niklaus, S., Snavely, N., Wang, O.: Neural scene flow fields for space-time view synthesis of dynamic scenes. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00643"},{"key":"8_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107112","volume":"99","author":"H Liu","year":"2020","unstructured":"Liu, H., Tang, X., Shen, S.: Depth-map completion for large indoor scene reconstruction. Pattern Recogn. 99, 107112 (2020)","journal-title":"Pattern Recogn."},{"issue":"10","key":"8_CR26","doi-asserted-by":"publisher","first-page":"2624","DOI":"10.1109\/TPAMI.2019.2930258","volume":"42","author":"C Luo","year":"2019","unstructured":"Luo, C., et al.: Every pixel counts++: joint learning of geometry and motion with 3D holistic understanding. TPAMI 42(10), 2624\u20132641 (2019)","journal-title":"TPAMI"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Martin-Brualla, R., Radwan, N., Sajjadi, M., Barron, J.T., Dosovitskiy, A., Duckworth, D.: NeRF in the wild: neural radiance fields for unconstrained photo collections. arXiv preprint arXiv:2008.02268 (2020)","DOI":"10.1109\/CVPR46437.2021.00713"},{"issue":"2","key":"8_CR28","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1109\/2945.468400","volume":"1","author":"N Max","year":"1995","unstructured":"Max, N.: Optical models for direct volume rendering. IEEE Trans. Visual. Comput. Graph. 1(2), 99\u2013108 (1995)","journal-title":"IEEE Trans. Visual. Comput. Graph."},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Meng, Y., et al.: SigNet: semantic instance aided unsupervised 3D geometry perception. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01004"},{"key":"8_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/978-3-030-58452-8_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Mildenhall","year":"2020","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405\u2013421. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_24"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Peng, R., Wang, R., Lai, Y., Tang, L., Cai, Y.: Excavating the potential capacity of self-supervised monocular depth estimation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01527"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Pillai, S., Ambru\u015f, R., Gaidon, A.: SuperDepth: self-supervised, super-resolved monocular depth estimation. In: ICRA (2019)","DOI":"10.1109\/ICRA.2019.8793621"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Corona, E., Pons-Moll, G., Moreno-Noguer, F.: D-NeRF: neural radiance fields for dynamic scenes. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Reading, C., Harakeh, A., Chae, J., Waslander, S.L.: Categorical depth distribution network for monocular 3d object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"8_CR35","unstructured":"Saxena, A., Chung, S.H., Ng, A.Y., et al.: Learning depth from single monocular images. In: NeurIPS (2005)"},{"key":"8_CR36","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":"8_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Sun, J., et al.: Disp R-CNN: Stereo 3D object detection via shape prior guided instance disparity estimation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01056"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Wang, C., Buenaposada, J.M., Zhu, R., Lucey, S.: Learning depth from monocular videos using direct methods. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00216"},{"issue":"4","key":"8_CR40","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":"8_CR41","doi-asserted-by":"crossref","unstructured":"Wei, Y., Liu, S., Rao, Y., Zhao, W., Lu, J., Zhou, J.: NerfingMVS: guided optimization of neural radiance fields for indoor multi-view stereo. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00556"},{"key":"8_CR42","doi-asserted-by":"crossref","unstructured":"Yang, N., Stumberg, L.v., Wang, R., Cremers, D.: D3VO: deep depth, deep pose and deep uncertainty for monocular visual odometry. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00136"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Yen-Chen, L., Florence, P., Barron, J.T., Rodriguez, A., Isola, P., Lin, T.Y.: iNeRF: inverting neural radiance fields for pose estimation. arXiv preprint arXiv:2012.05877 (2020)","DOI":"10.1109\/IROS51168.2021.9636708"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Yin, Z., Shi, J.: GeoNet: unsupervised learning of dense depth, optical flow and camera pose. In: CVPR, pp. 1983\u20131992 (2018)","DOI":"10.1109\/CVPR.2018.00212"},{"key":"8_CR45","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":"8_CR46","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"},{"issue":"11","key":"8_CR47","doi-asserted-by":"publisher","first-page":"3003","DOI":"10.1021\/acsphotonics.0c00997","volume":"7","author":"D Zhang","year":"2020","unstructured":"Zhang, D., Lo, F.P.W., Zheng, J.Q., Bai, W., Yang, G.Z., Lo, B.: Data-driven microscopic pose and depth estimation for optical microrobot manipulation. ACS Photonics 7(11), 3003\u20133014 (2020)","journal-title":"ACS Photonics"},{"key":"8_CR48","doi-asserted-by":"crossref","unstructured":"Zhao, W., Liu, S., Shu, Y., Liu, Y.J.: Towards better generalization: joint depth-pose learning without PoseNet. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00917"},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, J., Wang, Y., Qin, K., Zeng, W.: Unsupervised high-resolution depth learning from videos with dual networks. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00697"},{"key":"8_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.700"},{"key":"8_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Fan, X., Shi, P., Xin, Y.: R-MSFM: recurrent multi-scale feature modulation for monocular depth estimating. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01254"},{"key":"8_CR52","doi-asserted-by":"crossref","unstructured":"Zhu, S., Brazil, G., Liu, X.: The edge of depth: explicit constraints between segmentation and depth. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01313"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19842-7_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T18:59:14Z","timestamp":1710356354000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19842-7_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198410","9783031198427"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19842-7_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}