{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T18:40:07Z","timestamp":1751913607391,"version":"3.41.2"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030007669"},{"type":"electronic","value":"9783030007676"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-030-00767-6_2","type":"book-chapter","created":{"date-parts":[[2018,9,18]],"date-time":"2018-09-18T07:54:58Z","timestamp":1537257298000},"page":"13-23","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Depth Estimation from Monocular Images Using Dilated Convolution and Uncertainty Learning"],"prefix":"10.1007","author":[{"given":"Haojie","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinzhang","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lianghao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongxiao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,19]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440. IEEE, Boston (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"5","key":"2_CR2","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. 31(5), 824\u2013840 (2009)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Taylor, J., Shotton, J., Sharp, T., Fitzgibbon, A.: The Vitruvian manifold: inferring dense correspondences for one-shot human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 103\u2013110. IEEE, Providence (2012)","DOI":"10.1109\/CVPR.2012.6247664"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778. IEEE, Las Vegas (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Bertasius, G., Shi, J., Torresani, L.: DeepEdge: a multi-scale bifurcated deep network for top-down contour detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4380\u20134389. IEEE, Boston (2015)","DOI":"10.1109\/CVPR.2015.7299067"},{"issue":"1\u20133","key":"2_CR6","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1023\/A:1014573219977","volume":"47","author":"D Scharstein","year":"2002","unstructured":"Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Comput. Vis. 47(1\u20133), 7\u201342 (2002)","journal-title":"Int. J. Comput. Vis."},{"key":"2_CR7","series-title":"Texts in Computer Science","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/978-1-84882-935-7","volume-title":"Computer Vision","author":"R Szeliski","year":"2011","unstructured":"Szeliski, R.: Structure from motion. Computer Vision. Texts in Computer Science, pp. 303\u2013334. Springer, London (2011). https:\/\/doi.org\/10.1007\/978-1-84882-935-7"},{"issue":"4","key":"2_CR8","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541\u2013551 (1989)","journal-title":"Neural Comput."},{"key":"2_CR9","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: International Conference on Learning Representations, Caribe Hilton, Puerto Rico (2016)"},{"key":"2_CR10","unstructured":"Saxena, A., Chung, S.H., Ng, A.Y.: Learning depth from single monocular images. In: International Conference on Neural Information Processing Systems, pp. 1161\u20131168. MIT Press, Vancouver (2005)"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Ladicky, L., Shi, J., Pollefeys, M.: Pulling things out of perspective. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 89\u201396. IEEE, Columbus (2014)","DOI":"10.1109\/CVPR.2014.19"},{"key":"2_CR12","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., et al. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 775\u2013788. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_56"},{"key":"2_CR13","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Prediction from a single image using a multi-scale deep network. In: International Conference on Neural Information Processing Systems, pp. 2366\u20132374. MIT Press, Montreal (2014)"},{"key":"2_CR14","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. IEEE, Santiago (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Liu, F., Shen, C., Lin, G.: Deep convolutional neural fields for depth estimation from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5162\u20135170. IEEE, Boston (2015)","DOI":"10.1109\/CVPR.2015.7299152"},{"key":"2_CR16","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2800\u20132809. IEEE, Boston (2015)"},{"key":"2_CR17","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, Stanford (2016)","DOI":"10.1109\/3DV.2016.32"},{"key":"2_CR18","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., Vijay Kumar, B.G., 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"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6602\u20136611. IEEE, Honolulu (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Liu, M., Salzmann, M., He, X.: Discrete-continuous depth estimation from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 716\u2013723. IEEE, Columbus (2014)","DOI":"10.1109\/CVPR.2014.97"},{"key":"2_CR21","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":"2_CR22","unstructured":"Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: ENet: a deep neural network architecture for real-time semantic segmentation. CoRR abs\/1606.02147 (2016). http:\/\/arxiv.org\/abs\/1606.02147"},{"issue":"3","key":"2_CR23","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Roy, A., Todorovic, S.: Monocular depth estimation using neural regression forest. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5506\u20135514. IEEE, Las Vegas (2016)","DOI":"10.1109\/CVPR.2016.594"},{"key":"2_CR25","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 the IEEE Conference on Computer Vision and Pattern Recognition, pp. 161\u2013169. IEEE, Honolulu (2017)","DOI":"10.1109\/CVPR.2017.25"},{"key":"2_CR26","doi-asserted-by":"crossref","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1119\u20131127. IEEE, Boston (2015)","DOI":"10.1109\/CVPR.2015.7298715"}],"container-title":["Lecture Notes in Computer Science","Advances in Multimedia Information Processing \u2013 PCM 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-00767-6_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T18:22:08Z","timestamp":1751912528000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-00767-6_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030007669","9783030007676"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-00767-6_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"19 September 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PCM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim Conference on Multimedia","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hefei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"21 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pcm2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/pcm2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}