{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T17:54:08Z","timestamp":1772301248270,"version":"3.50.1"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012694","type":"print"},{"value":"9783030012700","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\/978-3-030-01270-0_50","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T22:07:51Z","timestamp":1538777271000},"page":"851-868","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":121,"title":["DeepTAM: Deep Tracking and Mapping"],"prefix":"10.1007","author":[{"given":"Huizhong","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Benjamin","family":"Ummenhofer","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Brox","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"50_CR1","unstructured":"Abadi, M., et al.: TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems (2015). Software available from: www.tensorflow.org"},{"key":"50_CR2","doi-asserted-by":"publisher","unstructured":"Agrawal, P., Carreira, J., Malik, J.: Learning to see by moving. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 37\u201345, Dec 2015. https:\/\/doi.org\/10.1109\/ICCV.2015.13","DOI":"10.1109\/ICCV.2015.13"},{"key":"50_CR3","doi-asserted-by":"publisher","unstructured":"Collins, R.T.: A space-sweep approach to true multi-image matching, pp. 358\u2013363. IEEE, June 1996. https:\/\/doi.org\/10.1109\/CVPR.1996.517097","DOI":"10.1109\/CVPR.1996.517097"},{"key":"50_CR4","doi-asserted-by":"publisher","unstructured":"Dhiman, V., Tran, Q.H., Corso, J.J., Chandraker, M.: A continuous occlusion model for road scene understanding. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4331\u20134339, June 2016. https:\/\/doi.org\/10.1109\/CVPR.2016.469","DOI":"10.1109\/CVPR.2016.469"},{"key":"50_CR5","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth Map Prediction from a Single Image using a Multi-Scale Deep Network. arXiv:1406.2283 [cs], June 2014"},{"issue":"3","key":"50_CR6","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1109\/TPAMI.2017.2658577","volume":"40","author":"J Engel","year":"2018","unstructured":"Engel, J., Koltun, V., Cremers, D.: Direct sparse odometry. IEEE Trans. Pattern Anal. Mach. Intell. 40(3), 611\u2013625 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2658577","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"50_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/978-3-319-10605-2_54","volume-title":"Computer Vision \u2013 ECCV 2014","author":"J Engel","year":"2014","unstructured":"Engel, J., Sch\u00f6ps, T., Cremers, D.: LSD-SLAM: large-scale direct monocular SLAM. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 834\u2013849. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_54"},{"key":"50_CR8","doi-asserted-by":"publisher","unstructured":"Fattal, R.: Single image dehazing. In: ACM SIGGRAPH 2008 Papers. SIGGRAPH 2008, pp. 72:1\u201372:9. ACM, New York (2008). https:\/\/doi.org\/10.1145\/1399504.1360671, http:\/\/doi.acm.org\/10.1145\/1399504.1360671","DOI":"10.1145\/1399504.1360671"},{"issue":"1","key":"50_CR9","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/s11263-006-7899-4","volume":"70","author":"PF Felzenszwalb","year":"2006","unstructured":"Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient belief propagation for early vision. Int. J. Comput. Vis. 70(1), 41\u201354 (2006). https:\/\/doi.org\/10.1007\/s11263-006-7899-4","journal-title":"Int. J. Comput. Vis."},{"key":"50_CR10","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"50_CR11","doi-asserted-by":"publisher","unstructured":"Gupta, S., Arbelez, P., Malik, J.: Perceptual organization and recognition of indoor scenes from rgb-d images. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp. 564\u2013571, June 2013. https:\/\/doi.org\/10.1109\/CVPR.2013.79","DOI":"10.1109\/CVPR.2013.79"},{"issue":"2","key":"50_CR12","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s11263-014-0777-6","volume":"112","author":"Saurabh Gupta","year":"2014","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. Int. J. Comput. Vision 112(2), 133\u2013149 (2015). https:\/\/doi.org\/10.1007\/s11263-014-0777-6, http:\/\/dx.doi.org\/10.1007\/s11263-014-0777-6","journal-title":"International Journal of Computer Vision"},{"key":"50_CR13","doi-asserted-by":"publisher","unstructured":"Hirschm\u00fcller, H.: Accurate and efficient stereo processing by semi-global matching and mutual information. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol. 2, pp. 807\u2013814, June 2005. https:\/\/doi.org\/10.1109\/CVPR.2005.56","DOI":"10.1109\/CVPR.2005.56"},{"issue":"2","key":"50_CR14","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/TPAMI.2012.156","volume":"35","author":"A Hosni","year":"2013","unstructured":"Hosni, A., Rhemann, C., Bleyer, M., Rother, C., Gelautz, M.: Fast cost-volume filtering for visual correspondence and beyond. IEEE Trans. Pattern Anal. Mach. Intell. 35(2), 504\u2013511 (2013). https:\/\/doi.org\/10.1109\/TPAMI.2012.156","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"50_CR15","doi-asserted-by":"publisher","unstructured":"Kendall, A., Martirosyan, H., Dasgupta, S., Henry, P.: End-to-end learning of geometry and context for deep stereo regression. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 66\u201375, Oct 2017. https:\/\/doi.org\/10.1109\/ICCV.2017.17","DOI":"10.1109\/ICCV.2017.17"},{"key":"50_CR16","doi-asserted-by":"crossref","unstructured":"Kendall, A., Cipolla, R.: Geometric loss functions for camera pose regression with deep learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.694"},{"key":"50_CR17","doi-asserted-by":"publisher","unstructured":"Kerl, C., Sturm, J., Cremers, D.: Dense visual SLAM for RGB-D cameras. In: 2013 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 2100\u20132106, Nov 2013. https:\/\/doi.org\/10.1109\/IROS.2013.6696650","DOI":"10.1109\/IROS.2013.6696650"},{"key":"50_CR18","doi-asserted-by":"publisher","unstructured":"Kerl, C., Sturm, J., Cremers, D.: Robust odometry estimation for RGB-D cameras. In: 2013 IEEE International Conference on Robotics and Automation, pp. 3748\u20133754, May 2013. https:\/\/doi.org\/10.1109\/ICRA.2013.6631104","DOI":"10.1109\/ICRA.2013.6631104"},{"key":"50_CR19","unstructured":"Kingma, D., Ba, J.: Adam: A Method for Stochastic Optimization. arXiv:1412.6980 [cs], Dec 2014"},{"key":"50_CR20","doi-asserted-by":"crossref","unstructured":"Li, R., Wang, S., Long, Z., Gu, D.: UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning. arXiv:1709.06841 [cs], Sept 2017","DOI":"10.1109\/ICRA.2018.8461251"},{"key":"50_CR21","unstructured":"Loshchilov, I., Hutter, F.: SGDR: Stochastic Gradient Descent with Warm Restarts. arXiv:1608.03983 [cs, math], Aug 2016"},{"issue":"2","key":"50_CR22","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91\u2013110 (2004). https:\/\/doi.org\/10.1023\/B:VISI.0000029664.99615.94","journal-title":"Int. J. Comput. Vis."},{"key":"50_CR23","doi-asserted-by":"publisher","unstructured":"Newcombe, R.A., Lovegrove, S., Davison, A.: DTAM: dense tracking and mapping in real-time. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 2320\u20132327 (2011). https:\/\/doi.org\/10.1109\/ICCV.2011.6126513","DOI":"10.1109\/ICCV.2011.6126513"},{"key":"50_CR24","doi-asserted-by":"publisher","unstructured":"Sch\u00f6nberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4104\u20134113, June 2016. https:\/\/doi.org\/10.1109\/CVPR.2016.445","DOI":"10.1109\/CVPR.2016.445"},{"key":"50_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1007\/978-3-319-46487-9_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"JL Sch\u00f6nberger","year":"2016","unstructured":"Sch\u00f6nberger, J.L., Zheng, E., Frahm, J.M., Pollefeys, M.: Pixelwise view selection for unstructured multi-view stereo. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 501\u2013518. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_31"},{"key":"50_CR26","doi-asserted-by":"publisher","unstructured":"Song, S., Chandraker, M.: Joint SFM and detection cues for monocular 3D localization in road scenes. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 3734\u20133742, June 2015. https:\/\/doi.org\/10.1109\/CVPR.2015.7298997","DOI":"10.1109\/CVPR.2015.7298997"},{"key":"50_CR27","doi-asserted-by":"publisher","unstructured":"Song, S., Yu, F., Zeng, A., Chang, A.X., Savva, M., Funkhouser, T.: Semantic scene completion from a single depth image. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 190\u2013198, July 2017. https:\/\/doi.org\/10.1109\/CVPR.2017.28","DOI":"10.1109\/CVPR.2017.28"},{"key":"50_CR28","doi-asserted-by":"publisher","unstructured":"Sturm, J., Engelhard, N., Endres, F., Burgard, W., Cremers, D.: A benchmark for the evaluation of RGB-D SLAM systems. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 573\u2013580, Oct 2012. https:\/\/doi.org\/10.1109\/IROS.2012.6385773","DOI":"10.1109\/IROS.2012.6385773"},{"key":"50_CR29","doi-asserted-by":"publisher","unstructured":"Tateno, K., Tombari, F., Laina, I., Navab, N.: CNN-SLAM: real-time dense monocular SLAM with learned depth prediction. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6565\u20136574, https:\/\/doi.org\/10.1109\/CVPR.2017.695, July 2017","DOI":"10.1109\/CVPR.2017.695"},{"key":"50_CR30","doi-asserted-by":"crossref","unstructured":"Ummenhofer, B., et al.: DeMoN: depth and motion network for learning monocular stereo. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.596"},{"key":"50_CR31","doi-asserted-by":"crossref","unstructured":"Valada, A., Radwan, N., Burgard, W.: Deep Auxiliary Learning for Visual Localization and Odometry. arXiv:1803.03642 [cs], Mar 2018","DOI":"10.1109\/ICRA.2018.8462979"},{"key":"50_CR32","unstructured":"Vijayanarasimhan, S., Ricco, S., Schmid, C., Sukthankar, R., Fragkiadaki, K.: SfM-Net: Learning of Structure and Motion from Video. arXiv:1704.07804 [cs], Apr 2017"},{"key":"50_CR33","doi-asserted-by":"publisher","unstructured":"Wang, S., Clark, R., Wen, H., Trigoni, N.: DeepVO: towards end-to-end visual odometry with deep recurrent convolutional neural networks. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 2043\u20132050, May 2017. https:\/\/doi.org\/10.1109\/ICRA.2017.7989236","DOI":"10.1109\/ICRA.2017.7989236"},{"key":"50_CR34","doi-asserted-by":"publisher","unstructured":"Xiao, J., Owens, A., Torralba, A.: SUN3D: a database of big spaces reconstructed using SfM and object labels. In: 2013 IEEE International Conference on Computer Vision (ICCV), pp. 1625\u20131632, Dec 2013. https:\/\/doi.org\/10.1109\/ICCV.2013.458","DOI":"10.1109\/ICCV.2013.458"},{"key":"50_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, H., Patel, V.M.: Densely connected pyramid dehazing network. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00337"},{"key":"50_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, H., Patel, V.M.: Density-aware single image de-raining using a multi-stream dense network. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00079"},{"key":"50_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised Learning of Depth and Ego-Motion from Video. arXiv:1704.07813 [cs], Apr 2017","DOI":"10.1109\/CVPR.2017.700"}],"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\/978-3-030-01270-0_50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:54:18Z","timestamp":1665017658000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01270-0_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012694","9783030012700"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01270-0_50","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":"6 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"}]}}