{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:34:21Z","timestamp":1779294861918,"version":"3.51.4"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012663","type":"print"},{"value":"9783030012670","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01267-0_4","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T17:02:36Z","timestamp":1538845356000},"page":"55-71","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":143,"title":["Look Deeper into Depth: Monocular Depth Estimation with Semantic Booster and Attention-Driven Loss"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0833-5115","authenticated-orcid":false,"given":"Jianbo","family":"Jiao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yibing","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rynson","family":"Lau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"4_CR1","unstructured":"Chen, W., Fu, Z., Yang, D., Deng, J.: Single-image depth perception in the wild. In: NIPS (2016)"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"4_CR3","unstructured":"Couprie, C., Farabet, C., Najman, L., LeCun, Y.: Indoor semantic segmentation using depth information (2013). arXiv preprint arXiv:1301.3572"},{"key":"4_CR4","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 (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"4_CR5","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: NIPS (2014)"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Garg, R., Carneiro, G., Reid, I.: Unsupervised cnn for single view depth estimation: geometry to the rescue. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The kitti vision benchmark suite. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Gupta, S., Arbelaez, P., Malik, J.: Perceptual organization and recognition of indoor scenes from rgb-d images. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.79"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Gupta, S., Girshick, R., Arbel\u00e1ez, P., Malik, J.: Learning rich features from rgb-d images for object detection and segmentation. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Hane, C., Zach, C., Cohen, A., Angst, R., Pollefeys, M.: Joint 3d scene reconstruction and class segmentation. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.20"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"He, S., Jiao, J., Zhang, X., Han, G., Lau, R.W.: Delving into salient object subitizing and detections. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.120"},{"issue":"3","key":"4_CR17","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1145\/1073204.1073232","volume":"24","author":"D Hoiem","year":"2005","unstructured":"Hoiem, D., Efros, A.A., Hebert, M.: Automatic photo pop-up. ACM TOG 24(3), 577\u2013584 (2005)","journal-title":"ACM TOG"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Jafari, O.H., Groth, O., Kirillov, A., Yang, M.Y., Rother, C.: Analyzing modular cnn architectures for joint depth prediction and semantic segmentation. In: ICRA (2017)","DOI":"10.1109\/ICRA.2017.7989537"},{"issue":"2","key":"4_CR20","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1007\/s11263-017-1015-9","volume":"124","author":"J Jiao","year":"2017","unstructured":"Jiao, J., Yang, Q., He, S., Gu, S., Zhang, L., Lau, R.W.: Joint image denoising and disparity estimation via stereo structure pca and noise-tolerant cost. IJCV 124(2), 204\u2013222 (2017)","journal-title":"IJCV"},{"issue":"11","key":"4_CR21","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(11), 2144\u20132158 (2014)","journal-title":"IEEE TPAMI"},{"key":"4_CR22","unstructured":"Kendall, A., Gal, Y.: What uncertainties do we need in bayesian deep learning for computer vision? In: NIPS (2017)"},{"key":"4_CR23","unstructured":"Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: CVPR (2018)"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Kim, S., Park, K., Sohn, K., Lin, S.: Unified depth prediction and intrinsic image decomposition from a single image via joint convolutional neural fields. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46484-8_9"},{"key":"4_CR25","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization (2014). arXiv preprint arXiv:1412.6980"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Kuznietsov, Y., St\u00fcckler, J., Leibe, B.: Semi-supervised deep learning for monocular depth map prediction. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.238"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Ladicky, L., Shi, J., Pollefeys, M.: Pulling things out of perspective. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.19"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., Navab, N.: Deeper depth prediction with fully convolutional residual networks. In: 3D Vision (3DV) (2016)","DOI":"10.1109\/3DV.2016.32"},{"key":"4_CR29","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 (2015)"},{"key":"4_CR30","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: ICCV (2017)","DOI":"10.1109\/ICCV.2017.365"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., Reid, I.: Refinenet: multi-path refinement networks for high-resolution semantic segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.549"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Liu, B., Gould, S., Koller, D.: Single image depth estimation from predicted semantic labels. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539823"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Liu, F., Shen, C., Lin, G.: Deep convolutional neural fields for depth estimation from a single image. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299152"},{"issue":"10","key":"4_CR35","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(10), 2024\u20132039 (2016)","journal-title":"IEEE TPAMI"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Liu, M., Salzmann, M., He, X.: Discrete-continuous depth estimation from a single image. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.97"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Misra, I., Shrivastava, A., Gupta, A., Hebert, M.: Cross-stitch networks for multi-task learning. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.433"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Pirsiavash, H., Ko\u0161eck\u00e1, J.: Joint semantic segmentation and depth estimation with deep convolutional networks. In: 3D Vision (3DV) (2016)","DOI":"10.1109\/3DV.2016.69"},{"key":"4_CR40","unstructured":"Paszke, A., et al.: Automatic differentiation in pytorch (2017)"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Qi, X., Liao, R., Jia, J., Fidler, S., Urtasun, R.: 3d graph neural networks for rgbd semantic segmentation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.556"},{"key":"4_CR42","unstructured":"Ren, X., Bo, L., Fox, D.: Rgb-(d) scene labeling: features and algorithms. In: CVPR (2012)"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Roy, A., Todorovic, S.: Monocular depth estimation using neural regression forest. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.594"},{"issue":"5","key":"4_CR44","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(5), 824\u2013840 (2009)","journal-title":"IEEE TPAMI"},{"key":"4_CR45","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.89"},{"key":"4_CR46","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":"4_CR47","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv preprint arXiv:1409.1556"},{"key":"4_CR48","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun rgb-d: a rgb-d scene understanding benchmark suite. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"4_CR49","doi-asserted-by":"crossref","unstructured":"Song, S., Yu, F., Zeng, A., Chang, A.X., Savva, M., Funkhouser, T.: Semantic scene completion from a single depth image. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.28"},{"key":"4_CR50","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1007\/978-3-319-46454-1_21","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Del Giorno","year":"2016","unstructured":"Del Giorno, A., Bagnell, J.A., Hebert, M.: A discriminative framework for anomaly detection in large videos. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 334\u2013349. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_21"},{"key":"4_CR51","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 (2015)"},{"key":"4_CR52","unstructured":"Wang, P., Shen, X., Russell, B., Cohen, S., Price, B., Yuille, A.L.: Surge: surface regularized geometry estimation from a single image. In: NIPS (2016)"},{"key":"4_CR53","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 (2017)","DOI":"10.1109\/CVPR.2017.25"},{"key":"4_CR54","unstructured":"Zagoruyko, S., Komodakis, N.: Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. In: ICLR (2017)"},{"key":"4_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.700"},{"key":"4_CR56","unstructured":"Zhuo, W., Salzmann, M., He, X., Liu, M.: Indoor scene structure analysis for single image depth estimation. In: CVPR (2015)"},{"key":"4_CR57","doi-asserted-by":"crossref","unstructured":"Zoran, D., Isola, P., Krishnan, D., Freeman, W.T.: Learning ordinal relationships for mid-level vision. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.52"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01267-0_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:09:40Z","timestamp":1665014980000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01267-0_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012663","9783030012670"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01267-0_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"7 October 2018","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":"Munich","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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","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":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}