{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T19:00:40Z","timestamp":1771614040383,"version":"3.50.1"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030336752","type":"print"},{"value":"9783030336769","type":"electronic"}],"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\/978-3-030-33676-9_20","type":"book-chapter","created":{"date-parts":[[2019,10,25]],"date-time":"2019-10-25T13:20:30Z","timestamp":1572009630000},"page":"288-302","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":40,"title":["SDNet: Semantically Guided Depth Estimation Network"],"prefix":"10.1007","author":[{"given":"Matthias","family":"Ochs","sequence":"first","affiliation":[]},{"given":"Adrian","family":"Kretz","sequence":"additional","affiliation":[]},{"given":"Rudolf","family":"Mester","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,10,25]]},"reference":[{"issue":"9","key":"20_CR1","doi-asserted-by":"publisher","first-page":"961","DOI":"10.1007\/s11263-018-1070-x","volume":"126","author":"H Alhaija","year":"2018","unstructured":"Alhaija, H., Mustikovela, S., Mescheder, L., Geiger, A., Rother, C.: Augmented reality meets computer vision: efficient data generation for urban driving scenes. Int. J. Comput. Vis. (IJCV) 126(9), 961\u2013972 (2018)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"20_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). \n                      https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"20_CR3","unstructured":"Cheng, J., Wang, Z., Pollastri, G.: A neural network approach to ordinal regression. In: International Joint Conference on Neural Networks, pp. 1279\u20131284 (2008)"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"20_CR5","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 (NIPS), pp. 2366\u20132374 (2014)"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K., Tao, D.: Deep ordinal regression network for monocular depth estimation. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2002\u20132011 (2018)","DOI":"10.1109\/CVPR.2018.00214"},{"key":"20_CR7","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). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46484-8_45"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Gidaris, S., Komodakis, N.: Detect, replace, refine: deep structured prediction for pixel wise labeling. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7187\u20137196 (2017)","DOI":"10.1109\/CVPR.2017.760"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6602\u20136611 (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"20_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1007\/978-3-030-01252-6_30","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Guo","year":"2018","unstructured":"Guo, X., Li, H., Yi, S., Ren, J., Wang, X.: Learning monocular depth by distilling cross-domain stereo networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 506\u2013523. Springer, Cham (2018). \n                      https:\/\/doi.org\/10.1007\/978-3-030-01252-6_30"},{"issue":"2","key":"20_CR11","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/TPAMI.2007.1166","volume":"30","author":"H Hirschm\u00fcller","year":"2008","unstructured":"Hirschm\u00fcller, H.: Stereo processing by semiglobal matching and mutual information. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 30(2), 328\u2013341 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Kn\u00f6belreiter, P., Reinbacher, C., Shekhovtsov, A., Pock, T.: End-to-end training of hybrid CNN-CRF models for stereo. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1456\u20131465 (2017)","DOI":"10.1109\/CVPR.2017.159"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Kong, S., Fowlkes, C.: Pixel-wise attentional gating for parsimonious pixel labeling. In: Winter Conference on Applications of Computer Vision (WACV) (2019)","DOI":"10.1109\/WACV.2019.00114"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Kuznietsov, Y., St\u00fcckler, J., Leibe, B.: Semi-supervised deep learning for monocular depth map prediction. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2215\u20132223 (2017)","DOI":"10.1109\/CVPR.2017.238"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Ladick\u00fd, L., Shi, J., Pollefeys, M.: Pulling things out of perspective. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 89\u201396 (2014)","DOI":"10.1109\/CVPR.2014.19"},{"key":"20_CR16","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":"20_CR17","unstructured":"Li, R., Xian, K., Shen, C., Cao, Z., Lu, H., Hang, L.: Deep attention-based classification network for robust depth prediction. CoRR arXiv, 1807.03959 [cs.CV] (2018)"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) (2018)","DOI":"10.1109\/TPAMI.2018.2858826"},{"issue":"10","key":"20_CR19","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. Pattern Anal. Mach. Intell. (TPAMI) 38(10), 2024\u20132039 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Liu, M., Salzmann, M., He, X.: Discrete-continuous depth estimation from a single image. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 716\u2013723 (2014)","DOI":"10.1109\/CVPR.2014.97"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Mayer, N., et al.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4040\u20134048 (2016)","DOI":"10.1109\/CVPR.2016.438"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Niu, Z., Zhou, M., Wang, L., Gao, X., Hua, G.: Ordinal regression with multiple output CNN for age estimation. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4920\u20134928 (2016)","DOI":"10.1109\/CVPR.2016.532"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Pang, J., Sun, W., SJ. Ren, J., Yang, C., Yan, Q.: Cascade residual learning: a two-stage convolutional neural network for stereo matching. In: International Conference on Computer Vision (ICCV) - Workshop, pp. 887\u2013895 (2017)","DOI":"10.1109\/ICCVW.2017.108"},{"key":"20_CR24","unstructured":"Saxena, A., Chung, S.H., Ng, A.Y.: Learning depth from single monocular images. In: Advances in Neural Information Processing Systems (NIPS), pp. 1161\u20131168 (2005)"},{"issue":"5","key":"20_CR25","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. Pattern Anal. Mach. Intell. (TPAMI) 31(5), 824\u2013840 (2009)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Schneider, L., et al.: Semantic stixels: depth is not enough. In: Intelligent Vehicles Symposium (IV), pp. 110\u2013117 (2016)","DOI":"10.1109\/IVS.2016.7535373"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., Geiger, A.: Sparsity invariant CNNs. In: International Conference on 3D Vision (3DV) (2017)","DOI":"10.1109\/3DV.2017.00012"},{"key":"20_CR28","first-page":"2287","volume":"17","author":"J \u017dbontar","year":"2016","unstructured":"\u017dbontar, J., LeCun, Y.: Stereo matching by training a convolutional neural network to compare image patches. J. Mach. Learn. Res. (JMLR) 17, 2287\u20132318 (2016)","journal-title":"J. Mach. Learn. Res. (JMLR)"},{"key":"20_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01261-8_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Wu","year":"2018","unstructured":"Wu, Y., He, K.: Group normalization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 3\u201319. Springer, Cham (2018). \n                      https:\/\/doi.org\/10.1007\/978-3-030-01261-8_1"},{"key":"20_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"842","DOI":"10.1007\/978-3-319-46493-0_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Xie","year":"2016","unstructured":"Xie, J., Girshick, R., Farhadi, A.: Deep3D: fully automatic 2D-to-3D video conversion with deep convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 842\u2013857. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46493-0_51"},{"key":"20_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1007\/978-3-030-01234-2_39","volume-title":"Computer Vision \u2013 ECCV 2018","author":"G Yang","year":"2018","unstructured":"Yang, G., Zhao, H., Shi, J., Deng, Z., Jia, J.: SegStereo: exploiting semantic information for disparity estimation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 660\u2013676. Springer, Cham (2018). \n                      https:\/\/doi.org\/10.1007\/978-3-030-01234-2_39"},{"key":"20_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1007\/978-3-030-01237-3_50","volume-title":"Computer Vision \u2013 ECCV 2018","author":"N Yang","year":"2018","unstructured":"Yang, N., Wang, R., St\u00fcckler, J., Cremers, D.: Deep virtual stereo odometry: leveraging deep depth prediction for monocular direct sparse odometry. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 835\u2013852. Springer, Cham (2018). \n                      https:\/\/doi.org\/10.1007\/978-3-030-01237-3_50"},{"key":"20_CR33","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1016\/j.patcog.2018.05.016","volume":"83","author":"Z Zhang","year":"2018","unstructured":"Zhang, Z., Xu, C., Yang, J., Tai, Y., Chen, L.: Deep hierarchical guidance and regularization learning for end-to-end depth estimation. Pattern Recogn. 83, 430\u2013442 (2018)","journal-title":"Pattern Recogn."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-33676-9_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,25]],"date-time":"2019-10-25T16:25:13Z","timestamp":1572020713000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-33676-9_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030336752","9783030336769"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-33676-9_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"25 October 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAGM GCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"German Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dortmund","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"41","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dagm2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/gcpr2019.tu-dortmund.de\/","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":"91","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":"43","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":"47% - 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":"5","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)"}}]}}