{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T12:50:47Z","timestamp":1742993447419,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030110086"},{"type":"electronic","value":"9783030110093"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-11009-3_19","type":"book-chapter","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T06:24:44Z","timestamp":1548311084000},"page":"324-336","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep Modular Network Architecture for Depth Estimation from Single Indoor Images"],"prefix":"10.1007","author":[{"given":"Seiya","family":"Ito","sequence":"first","affiliation":[]},{"given":"Naoshi","family":"Kaneko","sequence":"additional","affiliation":[]},{"given":"Yuma","family":"Shinohara","sequence":"additional","affiliation":[]},{"given":"Kazuhiko","family":"Sumi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,1,23]]},"reference":[{"key":"19_CR1","unstructured":"Chen, W., Fu, Z., Yang, D., Deng, J.: Single-image depth perception in the wild. In: NIPS, pp. 730\u2013738 (2016)"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Dasgupta, S., Fang, K., Chen, K., Savarese, S.: Delay: robust spatial layout estimation for cluttered indoor scenes. In: CVPR, pp. 616\u2013624 (2016)","DOI":"10.1109\/CVPR.2016.73"},{"key":"19_CR3","unstructured":"Dellaert, F., Seitz, S.M., Thorpe, C.E., Thrun, S.: Structure from motion without correspondence. In: CVPR, pp. 557\u2013564 (2000)"},{"key":"19_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, pp. 2650\u20132658 (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"19_CR5","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 (2014)"},{"key":"19_CR6","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html"},{"key":"19_CR7","unstructured":"Felzenszwalb, P., Huttenlocher, D.: Distance transforms of sampled functions. Technical report, Cornell University (2004)"},{"issue":"9","key":"19_CR8","doi-asserted-by":"publisher","first-page":"1917","DOI":"10.1109\/JSEN.2010.2101060","volume":"11","author":"S Foix","year":"2011","unstructured":"Foix, S., Alenya, G., Torras, C.: Lock-in time-of-flight (ToF) cameras: a survey. IEEE Sens. J. 11(9), 1917\u20131926 (2011)","journal-title":"IEEE Sens. J."},{"issue":"11","key":"19_CR9","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. 32(11), 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: CVPR, pp. 270\u2013279 (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"19_CR11","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NIPS, pp. 2672\u20132680 (2014)"},{"issue":"3","key":"19_CR12","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 Trans. Graph. 24(3), 577\u2013584 (2005)","journal-title":"ACM Trans. Graph."},{"key":"19_CR13","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, pp. 4620\u20134627 (2017)","DOI":"10.1109\/ICRA.2017.7989537"},{"key":"19_CR14","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"19_CR15","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: NIPS, pp. 109\u2013117 (2011)"},{"key":"19_CR16","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1097\u20131105 (2012)"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Kuznietsov, Y., St\u00fcckler, J., Leibe, B.: Semi-supervised deep learning for monocular depth map prediction. In: CVPR, pp. 6647\u20136655 (2017)","DOI":"10.1109\/CVPR.2017.238"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Ladicky, L., Shi, J., Pollefeys, M.: Pulling things out of perspective. In: CVPR, pp. 89\u201396 (2014)","DOI":"10.1109\/CVPR.2014.19"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Liu, B., Gould, S., Koller, D.: Single image depth estimation from predicted semantic labels. In: CVPR, pp. 1253\u20131260 (2010)","DOI":"10.1109\/CVPR.2010.5539823"},{"key":"19_CR20","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 (2015)","DOI":"10.1109\/CVPR.2015.7299152"},{"issue":"10","key":"19_CR21","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. 38(10), 2024\u20132039 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Liu, M., Salzmann, M., He, X.: Discrete-continuous depth estimation from a single image. In: CVPR, pp. 716\u2013723 (2014)","DOI":"10.1109\/CVPR.2014.97"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Roy, A., Todorovic, S.: Monocular depth estimation using neural regression forest. In: CVPR, pp. 5506\u20135514 (2016)","DOI":"10.1109\/CVPR.2016.594"},{"issue":"3","key":"19_CR24","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":"19_CR25","unstructured":"Saxena, A., Chung, S.H., Ng, A.Y.: Learning depth from single monocular images. In: NIPS, pp. 1161\u20131168 (2005)"},{"issue":"5","key":"19_CR26","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":"19_CR27","unstructured":"Scharstein, D., Szeliski, R.: High-accuracy stereo depth maps using structured light. In: CVPR, pp. 195\u2013202 (2003)"},{"key":"19_CR28","unstructured":"Seitz, S.M., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: A comparison and evaluation of multi-view stereo reconstruction algorithms. In: CVPR, pp. 519\u2013528 (2006)"},{"issue":"4","key":"19_CR29","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"E Shelhamer","year":"2017","unstructured":"Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 640\u2013651 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_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":"19_CR31","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"19_CR32","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":"19_CR33","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 (2015)"},{"key":"19_CR34","unstructured":"Yu, F., Zhang, Y., Song, S., Seff, A., Xiao, J.: LSUN: construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365 (2015)"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"19_CR36","unstructured":"Zhuo, W., Salzmann, M., He, X., Liu, M.: Indoor scene structure analysis for single image depth estimation. In: CVPR, pp. 614\u2013622 (2015)"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Zoran, D., Isola, P., Krishnan, D., Freeman, W.T.: Learning ordinal relationships for mid-level vision. In: ICCV, pp. 388\u2013396 (2015)","DOI":"10.1109\/ICCV.2015.52"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-11009-3_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T01:09:10Z","timestamp":1674349750000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-11009-3_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030110086","9783030110093"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-11009-3_19","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":"23 January 2019","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"}]}}