{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T16:10:53Z","timestamp":1783613453041,"version":"3.55.0"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585730","type":"print"},{"value":"9783030585747","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58574-7_35","type":"book-chapter","created":{"date-parts":[[2020,11,12]],"date-time":"2020-11-12T16:19:07Z","timestamp":1605197947000},"page":"581-597","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":109,"title":["Guiding Monocular Depth Estimation Using Depth-Attention Volume"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8311-1288","authenticated-orcid":false,"given":"Lam","family":"Huynh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9678-0886","authenticated-orcid":false,"given":"Phong","family":"Nguyen-Ha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0863-4844","authenticated-orcid":false,"given":"Jiri","family":"Matas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8767-0864","authenticated-orcid":false,"given":"Esa","family":"Rahtu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0073-0866","authenticated-orcid":false,"given":"Janne","family":"Heikkil\u00e4","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,13]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Bello, I., Zoph, B., Vaswani, A., Shlens, J., Le, Q.V.: Attention augmented convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3286\u20133295 (2019)","DOI":"10.1109\/ICCV.2019.00338"},{"key":"35_CR2","doi-asserted-by":"crossref","unstructured":"Chen, X., Chen, X., Zha, Z.J.: Structure-aware residual pyramid network for monocular depth estimation. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence, pp. 694\u2013700. AAAI Press (2019)","DOI":"10.24963\/ijcai.2019\/98"},{"key":"35_CR3","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"35_CR4","unstructured":"Dumoulin, V., Shlens, J., Kudlur, M.: A learned representation for artistic style. In: International Conference on Learning Representations ICLR (2017)"},{"key":"35_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: Proceedings of the IEEE International Conference on Computer Vision, pp. 2650\u20132658 (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"35_CR6","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, pp. 2366\u20132374 (2014)"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Facil, J.M., Ummenhofer, B., Zhou, H., Montesano, L., Brox, T., Civera, J.: CAM-convs: camera-aware multi-scale convolutions for single-view depth. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11826\u201311835 (2019)","DOI":"10.1109\/CVPR.2019.01210"},{"key":"35_CR8","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":"35_CR9","unstructured":"Geiger, A., Nie\u00dfner, M., Dai, A.: Robust vision challenge. In: CVPR Workshop (2018)"},{"key":"35_CR10","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: 2018 International Conference on 3D Vision (3DV), pp. 304\u2013313. IEEE (2018)","DOI":"10.1109\/3DV.2018.00043"},{"key":"35_CR11","volume-title":"Multiple View Geometry in Computer Vision","author":"R Hartley","year":"2003","unstructured":"Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003)"},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"35_CR13","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: IEEE Winter Conference on Applications of Computer Vision (WACV) (2019)","DOI":"10.1109\/WACV.2019.00116"},{"key":"35_CR14","series-title":"Advances in Computer Vision and Pattern Recognition","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-4640-7_8","volume-title":"Consumer Depth Cameras for Computer Vision","author":"A Janoch","year":"2013","unstructured":"Janoch, A., et al.: A category-level 3D object dataset: putting the kinect to work. In: Fossati, A., Gall, J., Grabner, H., Ren, X., Konolige, K. (eds.) Consumer Depth Cameras for Computer Vision. Advances in Computer Vision and Pattern Recognition. Springer, London (2013). https:\/\/doi.org\/10.1007\/978-1-4471-4640-7_8"},{"key":"35_CR15","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":"35_CR16","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"35_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/978-3-030-11015-4_25","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"T Koch","year":"2019","unstructured":"Koch, T., Liebel, L., Fraundorfer, F., K\u00f6rner, M.: Evaluation of CNN-based single-image depth estimation methods. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11131, pp. 331\u2013348. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11015-4_25"},{"key":"35_CR18","doi-asserted-by":"crossref","unstructured":"Kong, S., Fowlkes, C.: Pixel-wise attentional gating for scene parsing. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1024\u20131033. IEEE (2019)","DOI":"10.1109\/WACV.2019.00114"},{"key":"35_CR19","doi-asserted-by":"crossref","unstructured":"Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., Navab, N.: Deeper depth prediction with fully convolutional residual networks. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 239\u2013248. IEEE (2016)","DOI":"10.1109\/3DV.2016.32"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Lee, J.H., Kim, C.S.: Monocular depth estimation using relative depth maps. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2019)","DOI":"10.1109\/CVPR.2019.00996"},{"key":"35_CR21","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1016\/j.patcog.2018.05.029","volume":"83","author":"B Li","year":"2018","unstructured":"Li, B., Dai, Y., He, M.: Monocular depth estimation with hierarchical fusion of dilated CNNs and soft-weighted-sum inference. Pattern Recogn. 83, 328\u2013339 (2018)","journal-title":"Pattern Recogn."},{"key":"35_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1007\/978-3-030-20870-7_41","volume-title":"Computer Vision \u2013 ACCV 2018","author":"R Li","year":"2019","unstructured":"Li, R., Xian, K., Shen, C., Cao, Z., Lu, H., Hang, L.: Deep attention-based classification network for robust depth prediction. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11364, pp. 663\u2013678. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20870-7_41"},{"key":"35_CR23","doi-asserted-by":"crossref","unstructured":"Liu, C., Kim, K., Gu, J., Furukawa, Y., Kautz, J.: PlanerCNN: 3D plane detection and reconstruction from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4450\u20134459 (2019)","DOI":"10.1109\/CVPR.2019.00458"},{"key":"35_CR24","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2579\u20132588 (2018)","DOI":"10.1109\/CVPR.2018.00273"},{"key":"35_CR25","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32, pp. 8024\u20138035. Curran Associates, Inc. (2019). http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"35_CR26","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 the IEEE Conference on Computer Vision and Pattern Recognition, pp. 283\u2013291 (2018)","DOI":"10.1109\/CVPR.2018.00037"},{"key":"35_CR27","doi-asserted-by":"crossref","unstructured":"Ramamonjisoa, M., Lepetit, V.: SharpNet: fast and accurate recovery of occluding contours in monocular depth estimation. In: The IEEE International Conference on Computer Vision (ICCV) Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00266"},{"key":"35_CR28","unstructured":"Ren, H., El-khamy, M., Lee, J.: Deep robust single image depth estimation neural network using scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 37\u201345 (2019)"},{"key":"35_CR29","unstructured":"Saxena, A., Chung, S.H., Ng, A.Y.: Learning depth from single monocular images. In: Advances in Neural Information Processing Systems, pp. 1161\u20131168 (2006)"},{"key":"35_CR30","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":"35_CR31","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun RGB-D: A RGB-D scene understanding benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 567\u2013576 (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"35_CR32","doi-asserted-by":"publisher","unstructured":"Szeliski, R.: Structure from motion. In: Computer Vision. Texts in Computer Science, pp. 303\u2013334. Springer, London (2011). https:\/\/doi.org\/10.1007\/978-1-84882-935-0_7","DOI":"10.1007\/978-1-84882-935-0_7"},{"key":"35_CR33","doi-asserted-by":"crossref","unstructured":"Tan, M., et al.: MnasNet: platform-aware neural architecture search for mobile. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2820\u20132828 (2019)","DOI":"10.1109\/CVPR.2019.00293"},{"key":"35_CR34","unstructured":"Wang, F., et al.: Residual attention network for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2017)"},{"key":"35_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"35_CR36","doi-asserted-by":"crossref","unstructured":"Wofk, D., Ma, F., Yang, T.J., Karaman, S., Sze, V.: FastDepth: fast monocular depth estimation on embedded systems. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 6101\u20136108. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8794182"},{"key":"35_CR37","doi-asserted-by":"crossref","unstructured":"Xiao, J., Owens, A., Torralba, A.: Sun3D: a database of big spaces reconstructed using SFM and object labels. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1625\u20131632 (2013)","DOI":"10.1109\/ICCV.2013.458"},{"key":"35_CR38","doi-asserted-by":"crossref","unstructured":"Xu, D., Wang, W., Tang, H., Liu, H., Sebe, N., Ricci, E.: Structured attention guided convolutional neural fields for monocular depth estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3917\u20133925 (2018)","DOI":"10.1109\/CVPR.2018.00412"},{"key":"35_CR39","unstructured":"Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"35_CR40","doi-asserted-by":"crossref","unstructured":"Yin, W., Liu, Y., Shen, C., Yan, Y.: Enforcing geometric constraints of virtual normal for depth prediction. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00578"},{"key":"35_CR41","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: International Conference on Learning Representations (ICLR) (2016)"},{"key":"35_CR42","doi-asserted-by":"crossref","unstructured":"Yu, F., Koltun, V., Funkhouser, T.: Dilated residual networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 472\u2013480 (2017)","DOI":"10.1109\/CVPR.2017.75"},{"key":"35_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Physically-based rendering for indoor scene understanding using convolutional neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.537"},{"key":"35_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Cui, Z., Xu, C., Yan, Y., Sebe, N., Yang, J.: Pattern-affinitive propagation across depth, surface normal and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4106\u20134115 (2019)","DOI":"10.1109\/CVPR.2019.00423"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58574-7_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:11:15Z","timestamp":1731370275000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58574-7_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585730","9783030585747"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58574-7_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"13 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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":"7","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 due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","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)"}}]}}