{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:44:08Z","timestamp":1777653848866,"version":"3.51.4"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200854","type":"print"},{"value":"9783031200861","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\/978-3-031-20086-1_2","type":"book-chapter","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T10:31:55Z","timestamp":1668076315000},"page":"18-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Depth Map Decomposition for Monocular Depth Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8256-6846","authenticated-orcid":false,"given":"Jinyoung","family":"Jun","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3674-4023","authenticated-orcid":false,"given":"Jae-Han","family":"Lee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9329-7365","authenticated-orcid":false,"given":"Chul","family":"Lee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4276-1831","authenticated-orcid":false,"given":"Chang-Su","family":"Kim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"2_CR1","unstructured":"Bhat, S.F., Alhashim, I., Wonka, P.: AdaBins: depth estimation using adaptive bins. In: CVPR, pp. 4009\u20134018 (2021)"},{"key":"2_CR2","unstructured":"Chen, W., Fu, Z., Yang, D., Deng, J.: Single-image depth perception in the wild. In: NIPS, pp. 730\u2013738 (2016)"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Chen, X., Zha, Z.J.: Structure-aware residual pyramid network for monocular depth estimation. In: IJCAI, pp. 694\u2013700 (2019)","DOI":"10.24963\/ijcai.2019\/98"},{"key":"2_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 x 16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"2_CR5","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, pp. 2650\u20132658 (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"2_CR6","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: NIPS, pp. 2366\u20132374 (2014)"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K., Tao, D.: Deep ordinal regression network for monocular depth estimation. In: CVPR, pp. 2002\u20132011 (2018)","DOI":"10.1109\/CVPR.2018.00214"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Godard, C., Aodha, O.M., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: CVPR, pp. 270\u2013279 (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Gupta, A., Efros, A.A., Hebert, M.: Blocks world revisited: image understanding using qualitative geometry and mechanics. In: ECCV, pp. 482\u2013496 (2010)","DOI":"10.1007\/978-3-642-15561-1_35"},{"key":"2_CR10","unstructured":"Gupta, A., Hebert, M., Kanade, T., Blei, D.: Estimating spatial layout of rooms using volumetric reasoning about objects and surfaces. In: NIPS (2010)"},{"key":"2_CR11","unstructured":"Han, J., Pei, J., Kamber, M.: Data Mining: Concepts and Techniques. Elsevier (2011)"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Hao, Z., Li, Y., You, S., Lu, F.: Detail preserving depth estimation from a single image using attention guided networks. In: 3DV, pp. 304\u2013313 (2018)","DOI":"10.1109\/3DV.2018.00043"},{"key":"2_CR13","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":"2_CR14","doi-asserted-by":"crossref","unstructured":"Heo, M., Lee, J., Kim, K.R., Kim, H.U., Kim, C.S.: Monocular depth estimation using whole strip masking and reliability-based refinement. In: ECCV, pp. 36\u201351 (2018)","DOI":"10.1007\/978-3-030-01225-0_3"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Hu, J., Ozay, M., Zhang, Y., Okatani, T.: Revisiting single image depth estimation: toward higher resolution maps with accurate object boundaries. In: WACV, pp. 1043\u20131051 (2019)","DOI":"10.1109\/WACV.2019.00116"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Huynh, L., Nguyen-Ha, P., Matas, J., Rahtu, E., Heikkil\u00e4, J.: Guiding monocular depth estimation using depth-attention volume. In: ECCV, pp. 581\u2013597 (2020)","DOI":"10.1007\/978-3-030-58574-7_35"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: evolution of optical flow estimation with deep networks. In: CVPR, pp. 2462\u20132470 (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Izadinia, H., Shan, Q., Seitz, S.M.: IM2CAD. In: CVPR, pp. 5134\u20135143 (2017)","DOI":"10.1109\/CVPR.2017.260"},{"issue":"1\/2","key":"2_CR21","doi-asserted-by":"publisher","first-page":"81","DOI":"10.2307\/2332226","volume":"30","author":"MG Kendall","year":"1938","unstructured":"Kendall, M.G.: A new measure of rank correlation. Biometrika 30(1\/2), 81\u201393 (1938)","journal-title":"Biometrika"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Kim, H., et al.: Weighted joint-based human behavior recognition algorithm using only depth information for low-cost intelligent video-surveillance system. Expert Syst. Appl. 45, 131\u2013141 (2016)","DOI":"10.1016\/j.eswa.2015.09.035"},{"issue":"8","key":"2_CR23","doi-asserted-by":"publisher","first-page":"4131","DOI":"10.1109\/TIP.2018.2836318","volume":"27","author":"Y Kim","year":"2018","unstructured":"Kim, Y., Jung, H., Min, D., Sohn, K.: Deep monocular depth estimation via integration of global and local predictions. IEEE Trans. Image Process. 27(8), 4131\u20134144 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"2_CR24","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., Navab, N.: Deeper depth prediction with fully convolutional residual networks. In: 3DV, pp. 239\u2013248 (2016)","DOI":"10.1109\/3DV.2016.32"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Lee, J.H., Heo, M., Kim, K.R., Kim, C.S.: Single-image depth estimation based on Fourier domain analysis. In: CVPR, pp. 330\u2013339 (2018)","DOI":"10.1109\/CVPR.2018.00042"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Lee, J.H., Kim, C.S.: Monocular depth estimation using relative depth maps. In: CVPR, pp. 9729\u20139738 (2019)","DOI":"10.1109\/CVPR.2019.00996"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Lee, J.H., Kim, C.S.: Multi-loss rebalancing algorithm for monocular depth estimation. In: ECCV, pp. 785\u2013801 (2020)","DOI":"10.1007\/978-3-030-58520-4_46"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Lee, J.H., Lee, C., Kim, C.S.: Learning multiple pixelwise tasks based on loss scale balancing. In: ICCV, pp. 5107\u20135116 (2021)","DOI":"10.1109\/ICCV48922.2021.00506"},{"key":"2_CR30","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)"},{"issue":"3","key":"2_CR31","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1145\/1015706.1015780","volume":"23","author":"A Levin","year":"2004","unstructured":"Levin, A., Lischinski, D., Weiss, Y.: Colorization using optimization. ACM Trans. Graph. 23(3), 689\u2013694 (2004)","journal-title":"ACM Trans. Graph."},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Learning the depths of moving people by watching frozen people. In: CVPR, pp. 4521\u20134530 (2019)","DOI":"10.1109\/CVPR.2019.00465"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Li, Z., Snavely, N.: MegaDepth: learning single-view depth prediction from internet photos. In: CVPR, pp. 2041\u20132050 (2018)","DOI":"10.1109\/CVPR.2018.00218"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Lienen, J., Hullermeier, E., Ewerth, R., Nommensen, N.: Monocular depth estimation via listwise ranking using the Plackett-Luce model. In: CVPR, pp. 14595\u201314604 (2021)","DOI":"10.1109\/CVPR46437.2021.01436"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Liu, C., Yang, J., Ceylan, D., Yumer, E., Furukawa, Y.: PlaneNet: piece-wise planar reconstruction from a single RGB image. In: CVPR, pp. 2579\u20132588 (2018)","DOI":"10.1109\/CVPR.2018.00273"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: Progressive neural architecture search. In: ECCV, pp. 19\u201334 (2018)","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Liu, S., Johns, E., Davison, A.J.: End-to-end multi-task learning with attention. In: CVPR, pp. 1871\u20131880 (2019)","DOI":"10.1109\/CVPR.2019.00197"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Ma, F., Karaman, S.: Sparse-to-dense: depth prediction from sparse depth samples and a single image. In: ICRA, pp. 4796\u20134803 (2018)","DOI":"10.1109\/ICRA.2018.8460184"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Park, J., Joo, K., Hu, Z., Liu, C.K., So Kweon, I.: Non-local spatial propagation network for depth completion. In: ECCV, pp. 120\u2013136 (2020)","DOI":"10.1007\/978-3-030-58601-0_8"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Qi, X., Liao, R., Liu, Z., Urtasun, R., Jia, J.: GeoNet: geometric neural network for joint depth and surface normal estimation. In: CVPR, pp. 283\u2013291 (2018)","DOI":"10.1109\/CVPR.2018.00037"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Ramamonjisoa, M., Lepetit, V.: SharpNet: Fast and accurate recovery of occluding contours in monocular depth estimation. In: ICCVW (2019)","DOI":"10.1109\/ICCVW.2019.00266"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: ICCV, pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"2_CR43","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. (2020)"},{"issue":"5","key":"2_CR44","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1109\/TPAMI.2008.132","volume":"31","author":"A Saxena","year":"2008","unstructured":"Saxena, A., Sun, M., Ng, A.Y.: Make3D: learning 3D scene structure from a single still image. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 824\u2013840 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR45","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: ECCV, pp. 746\u2013760 (2012)","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: SUN RGB-D: a RGB-D scene understanding benchmark suite. In: CVPR, pp. 567\u2013576 (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"2_CR47","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: ICML, pp. 6105\u20136114 (2019)"},{"key":"2_CR48","doi-asserted-by":"crossref","unstructured":"Wang, C., Lucey, S., Perazzi, F., Wang, O.: Web stereo video supervision for depth prediction from dynamic scenes. In: 3DV, pp. 348\u2013357. IEEE (2019)","DOI":"10.1109\/3DV.2019.00046"},{"key":"2_CR49","unstructured":"Wang, P., Shen, X., Lin, Z., Cohen, S., Price, B., Yuille, A.L.: Towards unified depth and semantic prediction from a single image. In: CVPR, pp. 2800\u20132809 (2015)"},{"key":"2_CR50","doi-asserted-by":"crossref","unstructured":"Xian, K., et al.: Monocular relative depth perception with web stereo data supervision. In: CVPR, pp. 311\u2013320 (2018)","DOI":"10.1109\/CVPR.2018.00040"},{"key":"2_CR51","doi-asserted-by":"crossref","unstructured":"Xian, K., Zhang, J., Wang, O., Mai, L., Lin, Z., Cao, Z.: Structure-guided ranking loss for single image depth prediction. In: CVPR, pp. 611\u2013620 (2020)","DOI":"10.1109\/CVPR42600.2020.00069"},{"key":"2_CR52","doi-asserted-by":"crossref","unstructured":"Xie, J., Girshick, R., Farhadi, A.: Deep3D: fully automatic 2D-to-3D video conversion with deep convolutional neural networks. In: ECCV, pp. 842\u2013857 (2016)","DOI":"10.1007\/978-3-319-46493-0_51"},{"key":"2_CR53","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: CVPR, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"2_CR54","doi-asserted-by":"crossref","unstructured":"Xu, D., Ricci, E., Ouyang, W., Wang, X., Sebe, N.: Multi-scale continuous CRFs as sequential deep networks for monocular depth estimation. In: CVPR, pp. 5354\u20135362 (2017)","DOI":"10.1109\/CVPR.2017.25"},{"key":"2_CR55","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhu, X., Shi, J., Zhang, G., Bao, H., Li, H.: Depth completion from sparse LiDAR data with depth-normal constraints. In: ICCV, pp. 2811\u20132820 (2019)","DOI":"10.1109\/ICCV.2019.00290"},{"key":"2_CR56","doi-asserted-by":"crossref","unstructured":"Yin, W., Liu, Y., Shen, C., Yan, Y.: Enforcing geometric constraints of virtual normal for depth prediction. In: ICCV, pp. 5684\u20135693 (2019)","DOI":"10.1109\/ICCV.2019.00578"},{"key":"2_CR57","doi-asserted-by":"crossref","unstructured":"Yu, F., Koltun, V., Funkhouser, T.: Dilated residual networks. In: CVPR, pp. 472\u2013480 (2017)","DOI":"10.1109\/CVPR.2017.75"},{"key":"2_CR58","doi-asserted-by":"crossref","unstructured":"Zoran, D., Isola, P., Krishnan, D., Freeman, W.T.: Learning ordinal relationships for mid-level vision. In: ICCV, pp. 388\u2013396 (2015)","DOI":"10.1109\/ICCV.2015.52"}],"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\/978-3-031-20086-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T10:50:32Z","timestamp":1668077432000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20086-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200854","9783031200861"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20086-1_2","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":"11 November 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)"}}]}}