{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:55:30Z","timestamp":1740099330419,"version":"3.37.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030208899"},{"type":"electronic","value":"9783030208905"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-20890-5_24","type":"book-chapter","created":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T11:18:34Z","timestamp":1559387914000},"page":"365-380","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A CNN-Based Depth Estimation Approach with Multi-scale Sub-pixel Convolutions and a Smoothness Constraint"],"prefix":"10.1007","author":[{"given":"Shiyu","family":"Zhao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4360-5523","authenticated-orcid":false,"given":"Lin","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Ying","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Yongning","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,6,2]]},"reference":[{"key":"24_CR1","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. IEEE (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"24_CR2","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. MIT Press (2014)"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Eitel, A., Springenberg, J.T., Spinello, L., Riedmiller, M., Burgard, W.: Multimodal deep learning for robust RGB-D object recognition. In: IROS, pp. 681\u2013687. IEEE (2015)","DOI":"10.1109\/IROS.2015.7353446"},{"key":"24_CR4","first-page":"249","volume":"9","author":"X Glorot","year":"2010","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. JMLR 9, 249\u2013256 (2010)","journal-title":"JMLR"},{"key":"24_CR5","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s11263-014-0777-6","volume":"112","author":"S Gupta","year":"2015","unstructured":"Gupta, S., Arbel\u00e1ez, P., Girshick, R., Malik, J.: Indoor scene understanding with RGB-D images: bottom-up segmentation, object detection and semantic segmentation. IJCV 112, 133\u2013149 (2015)","journal-title":"IJCV"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778. IEEE (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"24_CR7","unstructured":"Hirschmuller, H.: Accurate and efficient stereo processing by semi-global matching and mutual information. In: CVPR, pp. 807\u2013814. IEEE (2005)"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Maaten, L.V.D., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, pp. 2261\u20132269. IEEE (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"24_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1007\/978-3-642-33715-4_56","volume-title":"Computer Vision \u2013 ECCV 2012","author":"K Karsch","year":"2012","unstructured":"Karsch, K., Liu, C., Kang, S.B.: Depth extraction from video using non-parametric sampling. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 775\u2013788. Springer, Heidelberg (2012). \n                      https:\/\/doi.org\/10.1007\/978-3-642-33715-4_56"},{"key":"24_CR10","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 Trans. PAMI 36, 2144\u20132158 (2014)","journal-title":"IEEE Trans. PAMI"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Konrad, J., Wang, M., Ishwar, P.: 2D-to-3D image conversion by learning depth from examples. In: CVPRW, pp. 16\u201322. IEEE (2012)","DOI":"10.1109\/CVPRW.2012.6238903"},{"key":"24_CR12","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. IEEE (2016)","DOI":"10.1109\/3DV.2016.32"},{"key":"24_CR13","unstructured":"Li, B., Shen, C., Dai, Y., van den Hengel, A., He, M.: Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs. In: CVPR, pp. 1119\u20131127. IEEE (2015)"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Li, J., Klein, R., Yao, A.: A two-streamed network for estimating fine-scaled depth maps from single RGB images. In: CVPR, pp. 3372\u20133380. IEEE (2017)","DOI":"10.1109\/ICCV.2017.365"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Liu, B., Gould, S., Koller, D.: Single image depth estimation from predicted semantic labels. In: CVPR, pp. 1253\u20131260. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539823"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Liu, F., Shen, C., Lin, G.: Deep convolutional neural fields for depth estimation from a single image. In: CVPR, pp. 5162\u20135170. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7299152"},{"key":"24_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 Trans. PAMI 38, 2024\u20132039 (2016)","journal-title":"IEEE Trans. PAMI"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Liu, M., Salzmann, M., He, X.: Discrete-continuous depth estimation from a single image. In: CVPR, pp. 716\u2013723. IEEE (2014)","DOI":"10.1109\/CVPR.2014.97"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Pirsiavash, H., Ko\u0161eck\u00e1, J.: Joint semantic segmentation and depth estimation with deep convolutional networks. In: 3DV, pp. 611\u2013619. IEEE (2016)","DOI":"10.1109\/3DV.2016.69"},{"key":"24_CR20","unstructured":"Ren, X., Bo, L., Fox, D.: RGB-(D) scene labeling: features and algorithms. In: CVPR, pp. 2759\u20132766. IEEE (2012)"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Roy, A., Todorovic, S.: Monocular depth estimation using neural regression forest. In: CVPR, pp. 5506\u20135514. IEEE (2016)","DOI":"10.1109\/CVPR.2016.594"},{"key":"24_CR22","unstructured":"Saxena, A., Chung, S.H., Ng, A.Y.: Learning depth from single monocular images. In: NIPS, pp. 1161\u20131168. MIT Press (2006)"},{"key":"24_CR23","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 Trans. PAMI 31, 824\u2013840 (2009)","journal-title":"IEEE Trans. PAMI"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Seki, A., Pollefeys, M.: SGM-Nets: semi-global matching with neural networks. In: CVPRW, pp. 21\u201326. IEEE (2017)","DOI":"10.1109\/CVPR.2017.703"},{"key":"24_CR25","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: CVPR, pp. 1874\u20131883. IEEE (2016)","DOI":"10.1109\/CVPR.2016.207"},{"key":"24_CR26","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, Part V. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). \n                      https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"24_CR27","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. IEEE (2015)"},{"key":"24_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1007\/978-3-319-04114-8_38","volume-title":"MultiMedia Modeling","author":"Z Wang","year":"2014","unstructured":"Wang, Z., Liu, H., Wang, X., Qian, Y.: Segment and label indoor scene based on RGB-D for the visually impaired. In: Gurrin, C., Hopfgartner, F., Hurst, W., Johansen, H., Lee, H., O\u2019Connor, N. (eds.) MMM 2014, Part I. LNCS, vol. 8325, pp. 449\u2013460. Springer, Cham (2014). \n                      https:\/\/doi.org\/10.1007\/978-3-319-04114-8_38"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Xie, S., Tu, Z.: Holistically-nested edge detection. In: ICCV, pp. 1395\u20131403. IEEE (2015)","DOI":"10.1109\/ICCV.2015.164"},{"key":"24_CR30","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. 161\u2013169. IEEE (2017)","DOI":"10.1109\/CVPR.2017.25"},{"key":"24_CR31","doi-asserted-by":"publisher","first-page":"1426","DOI":"10.1109\/TPAMI.2018.2839602","volume":"41","author":"D Xu","year":"2018","unstructured":"Xu, D., Ricci, E., Ouyang, W., Wang, X., Sebe, N.: Monocular depth estimation using multi-scale continuous CRFs as sequential deep networks. IEEE Trans. PAMI 41, 1426\u20131440 (2018). (Early Access)","journal-title":"IEEE Trans. PAMI"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Zbontar, J., LeCun, Y.: Stereo matching by training a convolutional neural network to compare image patches. JMLR, 2287\u20132318 (2016)","DOI":"10.1109\/CVPR.2015.7298767"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Zeng, A., Song, S., Nie\u00dfner, M., Fisher, M., Xiao, J., Funkhouser, T.: 3DMatch: learning local geometric descriptors from RGB-D reconstructions. In: CVPR, pp. 199\u2013208. IEEE (2017)","DOI":"10.1109\/CVPR.2017.29"},{"key":"24_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1007\/978-3-319-46454-1_52","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Y Zhang","year":"2016","unstructured":"Zhang, Y., et al.: Search-based depth estimation via coupled dictionary learning with large-margin structure inference. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part V. LNCS, vol. 9909, pp. 858\u2013874. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46454-1_52"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20890-5_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T11:24:46Z","timestamp":1559388286000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20890-5_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208899","9783030208905"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20890-5_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"2 June 2019","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":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.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"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"979","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"274","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"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"}},{"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"}},{"value":"2.7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}