{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T17:11:20Z","timestamp":1742922680111,"version":"3.40.3"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030695347"},{"type":"electronic","value":"9783030695354"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69535-4_27","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T15:13:11Z","timestamp":1614179591000},"page":"437-453","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cascaded Transposed Long-Range Convolutions for Monocular Depth Estimation"],"prefix":"10.1007","author":[{"given":"Go","family":"Irie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daiki","family":"Ikami","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takahito","family":"Kawanishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunio","family":"Kashino","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"27_CR1","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Proceedings of NeurIPS (2014)"},{"key":"27_CR2","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 ICCV (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Laina, I., Rupprecht, C., Belagiannis, V.: Deeper depth prediction with fully convolutional residual networks. In: Proceedings of 3DV (2016)","DOI":"10.1109\/3DV.2016.32"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Ma, F., Karaman, S.: Sparse-to-dense: depth prediction from sparse depth samples and a single image. In: Proceedings of ICRA (2018)","DOI":"10.1109\/ICRA.2018.8460184"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Godard, C., Aodha, O.M., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"27_CR6","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: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.25"},{"key":"27_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: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00214"},{"key":"27_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1007\/978-3-030-01225-0_11","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Z Chen","year":"2018","unstructured":"Chen, Z., Badrinarayanan, V., Drozdov, G., Rabinovich, A.: Estimating depth from RGB and sparse sensing. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 176\u2013192. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_11"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Ron, D., Duan, K., Ma, C., Xu, N., Wang, S., Hanumante, S., Sagar, D.: Monocular depth estimation via deep structured models with ordinal constraints. In: Proceedings of 3DV (2018)","DOI":"10.1109\/3DV.2018.00071"},{"key":"27_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/978-3-030-01225-0_3","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Heo","year":"2018","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: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 39\u201355. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_3"},{"key":"27_CR11","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":"27_CR12","first-page":"1231","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. IJRR 32, 1231\u20131237 (2013)","journal-title":"IJRR"},{"key":"27_CR13","unstructured":"Saxena, A., Chung, S.H., Ng, A.Y.: Learning depth from single monocular images. In: Proceedings of NeurIPS (2006)"},{"key":"27_CR14","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1109\/TPAMI.2008.132","volume":"31","author":"A Saxena","year":"2009","unstructured":"Saxena, A., Sun, M., Ng, A.Y.: Make3D: learning 3D scene structure from a single still image. IEEE TPAMI 31, 824\u2013840 (2009)","journal-title":"IEEE TPAMI"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Liu, B., Gould, S., Koller, D.: Single image depth estimation from predicted semantic labels. In: Proceedings of CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539823"},{"key":"27_CR16","doi-asserted-by":"publisher","first-page":"2144","DOI":"10.1109\/TPAMI.2014.2316835","volume":"36","author":"K Karsch","year":"2014","unstructured":"Karsch, K., Liu, C., Kang, S.B.: Depth transfer: Depth extraction from video using non-parametric sampling. IEEE TPAMI 36, 2144\u20132158 (2014)","journal-title":"IEEE TPAMI"},{"key":"27_CR17","doi-asserted-by":"publisher","first-page":"2024","DOI":"10.1109\/TPAMI.2015.2505283","volume":"38","author":"F Liu","year":"2016","unstructured":"Liu, F., Shen, C., Lin, G., Reid, I.: Learning depth from single monocular images using deep convolutional neural fields. IEEE TPAMI 38, 2024\u20132039 (2016)","journal-title":"IEEE TPAMI"},{"key":"27_CR18","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: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00042"},{"key":"27_CR19","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE TPAMI 40, 834\u2013848 (2017)","journal-title":"IEEE TPAMI"},{"key":"27_CR20","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. In: arXiv preprint arXiv:1907.10326. (2019)"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Yang, M., Yu, K., Zhang, C., Li, Z., Yang, K.: DenseASPP for semantic segmentation in street scenes. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00388"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Irie, G., Kawanishi, T., Kashino, K.: Robust learning for deep monocular depth estimation. In: Proceedings of ICIP (2019)","DOI":"10.1109\/ICIP.2019.8803059"},{"key":"27_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/978-3-030-01267-0_4","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Jiao","year":"2018","unstructured":"Jiao, J., Cao, Y., Song, Y., Lau, R.: Look deeper into depth: monocular depth estimation with semantic booster and attention-driven loss. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 55\u201371. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_4"},{"key":"27_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-030-01270-0_7","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Cheng","year":"2018","unstructured":"Cheng, X., Wang, P., Yang, R.: Depth estimation via affinity learned with convolutional spatial propagation network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 108\u2013125. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_7"},{"key":"27_CR25","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: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00037"},{"key":"27_CR26","unstructured":"Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: Proceedings of NeurIPS (2017)"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"27_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1007\/978-3-030-01219-9_14","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Gan","year":"2018","unstructured":"Gan, Y., Xu, X., Sun, W., Lin, L.: Monocular depth estimation with affinity, vertical pooling, and label enhancement. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 232\u2013247. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_14"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Rengarajan, V., Balaji, Y., Rajagopalan, A.N.: Unrolling the shutter: CNN to correct motion distortions. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.252"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Tian, Z., He, T., Shen, C., Yan, Y.: Decoders matter for semantic segmentation: data-dependent decoding enables flexible feature aggregation. In: Proceedings of CVPR (2019)","DOI":"10.1109\/CVPR.2019.00324"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: CCNet: criss-cross attention for semantic segmentation. In: Proceedings of ICCV (2019)","DOI":"10.1109\/ICCV.2019.00069"},{"key":"27_CR33","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: Proceedings of ICML (2019)"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"van Dijk, T., de Croon, G.: How do neural networks see depth in single images? In: Proceedings of ICCV (2019)","DOI":"10.1109\/ICCV.2019.00227"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: arXiv preprint arXiv:1609.05158. (2016)","DOI":"10.1109\/CVPR.2016.207"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: Inverted residuals and linear bottlenecks. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"27_CR39","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, S., Drozdzal, M., V\u00e1zquez, D., Romero, A., Bengio, Y.: The one hundred layers tiramisu: fully convolutional densenets for semantic segmentation. In: Proceedings of CVPR Workshops (2017)","DOI":"10.1109\/CVPRW.2017.156"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Lee, J.H., Kim, C.S.: Monocular depth estimation using relative depth maps. In: Proceedings of CVPR (2019)","DOI":"10.1109\/CVPR.2019.00996"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Kuznietsov, Y., St\u00fcckler, J., Leibe, B.: Semi-supervised deep learning for monocular depth map prediction. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.238"},{"key":"27_CR42","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"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69535-4_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T15:57:29Z","timestamp":1614182249000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69535-4_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695347","9783030695354"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69535-4_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","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":"254","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":"33% - 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","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","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)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}