{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T20:52:51Z","timestamp":1762980771228,"version":"3.37.3"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,9,3]],"date-time":"2019-09-03T00:00:00Z","timestamp":1567468800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,9,3]],"date-time":"2019-09-03T00:00:00Z","timestamp":1567468800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1007\/s11263-019-01221-0","type":"journal-article","created":{"date-parts":[[2019,9,3]],"date-time":"2019-09-03T13:10:31Z","timestamp":1567516231000},"page":"756-769","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["DeepTAM: Deep Tracking and Mapping with Convolutional Neural Networks"],"prefix":"10.1007","volume":"128","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4016-2250","authenticated-orcid":false,"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":[[2019,9,3]]},"reference":[{"key":"1221_CR1","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Man\u00e9, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Vi\u00e9gas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., & Zheng, X. (2015). TensorFlow: Large-scale machine learning on heterogeneous systems. Software available from tensorflow.org."},{"key":"1221_CR2","doi-asserted-by":"publisher","unstructured":"Agrawal, P., Carreira, J., & Malik, J. (2015). Learning to see by moving. In 2015 IEEE international conference on computer vision (ICCV) (pp. 37\u201345), \nhttps:\/\/doi.org\/10.1109\/ICCV.2015.13\n\n.","DOI":"10.1109\/ICCV.2015.13"},{"key":"1221_CR3","doi-asserted-by":"publisher","unstructured":"Collins, R.T. (1996). A space-sweep approach to true multi-image matching. In Proceedings CVPR IEEE computer society conference on computer vision and pattern recognition, IEEE (pp. 358\u2013363), \nhttps:\/\/doi.org\/10.1109\/CVPR.1996.517097\n\n.","DOI":"10.1109\/CVPR.1996.517097"},{"key":"1221_CR4","doi-asserted-by":"publisher","unstructured":"Dhiman, V., Tran, Q.H., Corso, J.J., & Chandraker, M. (2016). A continuous occlusion model for road scene understanding. In 2016 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 4331\u20134339), \nhttps:\/\/doi.org\/10.1109\/CVPR.2016.469\n\n.","DOI":"10.1109\/CVPR.2016.469"},{"key":"1221_CR5","unstructured":"Eigen, D., Puhrsch, C., & Fergus, R. (2014). Depth map prediction from a single image using a multi-scale deep network. In Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, & K. Q. Weinberger (Eds.) Advances in neural information processing systems (Vol. 27, pp. 2366\u20132374), Curran Associates, Inc."},{"key":"1221_CR6","doi-asserted-by":"crossref","unstructured":"Engel, J., Sch\u00f6ps, T., & Cremers, D. (2014). LSD-SLAM: Large-scale direct monocular SLAM. In European conference on computer vision (pp. 834\u2013849). Springer.","DOI":"10.1007\/978-3-319-10605-2_54"},{"issue":"3","key":"1221_CR7","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. (2018). Direct sparse odometry. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(3), 611\u2013625. \nhttps:\/\/doi.org\/10.1109\/TPAMI.2017.2658577\n\n.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1221_CR8","doi-asserted-by":"publisher","unstructured":"Fattal, R. (2008). Single image dehazing. In ACM SIGGRAPH 2008 Papers, ACM, New York, NY, USA, SIGGRAPH \u201908 (pp. 72:1\u201372:9), \nhttps:\/\/doi.org\/10.1145\/1399504.1360671\n\n.","DOI":"10.1145\/1399504.1360671"},{"issue":"1","key":"1221_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. (2006). Efficient belief propagation for early vision. International Journal of Computer Vision, 70(1), 41\u201354. \nhttps:\/\/doi.org\/10.1007\/s11263-006-7899-4\n\n.","journal-title":"International Journal of Computer Vision"},{"key":"1221_CR10","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., & Urtasun, R. (2012). Are we ready for autonomous driving? The kitti vision benchmark suite. In 2012 IEEE conference on computer vision and pattern recognition (CVPR), IEEE (pp. 3354\u20133361).","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"1221_CR11","doi-asserted-by":"publisher","unstructured":"Gupta, S., Arbel\u00e0ez, P., & Malik, J. (2013). Perceptual organization and recognition of indoor scenes from rgb-d images. In 2013 IEEE conference on computer vision and pattern recognition (pp. 564\u2013571), \nhttps:\/\/doi.org\/10.1109\/CVPR.2013.79\n\n.","DOI":"10.1109\/CVPR.2013.79"},{"issue":"2","key":"1221_CR12","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s11263-014-0777-6","volume":"112","author":"S Gupta","year":"2015","unstructured":"Gupta, S., Arbel\u00e1ez, P., Girshick, R., & Malik, J. (2015). Indoor scene understanding with rgb-d images: Bottom-up segmentation, object detection and semantic segmentation. International Journal of Computer Vision, 112(2), 133\u2013149. \nhttps:\/\/doi.org\/10.1007\/s11263-014-0777-6\n\n.","journal-title":"International Journal of Computer Vision"},{"key":"1221_CR13","doi-asserted-by":"publisher","unstructured":"Hirschm\u00fcller, H. (2005). 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), \nhttps:\/\/doi.org\/10.1109\/CVPR.2005.56\n\n.","DOI":"10.1109\/CVPR.2005.56"},{"issue":"2","key":"1221_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. (2013). Fast cost-volume filtering for visual correspondence and beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(2), 504\u2013511. \nhttps:\/\/doi.org\/10.1109\/TPAMI.2012.156\n\n.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1221_CR15","doi-asserted-by":"crossref","unstructured":"Kendall, A., & Cipolla, R. (2017). Geometric loss functions for camera pose regression with deep learning. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2017.694"},{"key":"1221_CR16","doi-asserted-by":"publisher","unstructured":"Kendall, A., Martirosyan, H., Dasgupta, S., & Henry, P. (2017). End-to-end learning of geometry and context for deep stereo regression. In 2017 IEEE international conference on computer vision (ICCV) (pp. 66\u201375), \nhttps:\/\/doi.org\/10.1109\/ICCV.2017.17\n\n.","DOI":"10.1109\/ICCV.2017.17"},{"key":"1221_CR17","doi-asserted-by":"publisher","unstructured":"Kerl, C., Sturm, J., & Cremers, D. (2013a). Dense visual SLAM for RGB-D cameras. In 2013 IEEE\/RSJ international conference on intelligent robots and systems (pp. 2100\u20132106), \nhttps:\/\/doi.org\/10.1109\/IROS.2013.6696650\n\n.","DOI":"10.1109\/IROS.2013.6696650"},{"key":"1221_CR18","doi-asserted-by":"publisher","unstructured":"Kerl, C., Sturm, J., & Cremers, D. (2013b). Robust odometry estimation for RGB-D cameras. In 2013 IEEE international conference on robotics and automation (pp. 3748\u20133754), \nhttps:\/\/doi.org\/10.1109\/ICRA.2013.6631104\n\n.","DOI":"10.1109\/ICRA.2013.6631104"},{"key":"1221_CR19","unstructured":"Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In Y. Bengio , Y. LeCun (Eds.) 3rd international conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings."},{"key":"1221_CR20","doi-asserted-by":"crossref","unstructured":"Klein, G., & Murray, D. (2007). Parallel tracking and mapping for small $$\\{\\text{AR}\\}$$ workspaces. In Proceedings of sixth IEEE and ACM international symposium on mixed and augmented reality (ISMAR\u201907).","DOI":"10.1109\/ISMAR.2007.4538852"},{"key":"1221_CR21","doi-asserted-by":"publisher","unstructured":"Li, R., Wang, S., Long, Z., & Gu, D. (2018). UnDeepVO: monocular visual odometry through unsupervised deep learning. In 2018 IEEE international conference on robotics and automation (ICRA) (pp. 7286\u20137291), \nhttps:\/\/doi.org\/10.1109\/ICRA.2018.8461251\n\n.","DOI":"10.1109\/ICRA.2018.8461251"},{"key":"1221_CR22","unstructured":"Loshchilov, I., & Hutter, F. (2017). SGDR: Stochastic gradient descent with warm restarts. In 5th international conference on learning representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings, OpenReview.net."},{"issue":"2","key":"1221_CR23","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. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91\u2013110. \nhttps:\/\/doi.org\/10.1023\/B:VISI.0000029664.99615.94\n\n.","journal-title":"International Journal of Computer Vision"},{"key":"1221_CR24","doi-asserted-by":"publisher","unstructured":"Newcombe, R. A., Lovegrove, S., & Davison, A. (2011). DTAM: Dense tracking and mapping in real-time. In: 2011 IEEE international conference on computer vision (ICCV) (pp. 2320\u20132327), \nhttps:\/\/doi.org\/10.1109\/ICCV.2011.6126513\n\n.","DOI":"10.1109\/ICCV.2011.6126513"},{"key":"1221_CR25","doi-asserted-by":"publisher","unstructured":"Sch\u00f6nberger, J. L., & Frahm, J. M. (2016). Structure-from-motion revisited. In 2016 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 4104\u20134113), \nhttps:\/\/doi.org\/10.1109\/CVPR.2016.445\n\n.","DOI":"10.1109\/CVPR.2016.445"},{"key":"1221_CR26","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1007\/978-3-319-46487-9_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Johannes L. Sch\u00f6nberger","year":"2016","unstructured":"Sch\u00f6nberger, J. L., Zheng, E., Frahm, J. M., & Pollefeys, M. (2016). Pixelwise view selection for unstructured multi-view stereo. In Computer Vision \u2013 ECCV 2016 (pp. 501\u2013518). Springer, \nhttps:\/\/doi.org\/10.1007\/978-3-319-46487-9_31\n\n."},{"key":"1221_CR27","doi-asserted-by":"publisher","unstructured":"Song, S., & Chandraker, M. (2015). 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), \nhttps:\/\/doi.org\/10.1109\/CVPR.2015.7298997\n\n.","DOI":"10.1109\/CVPR.2015.7298997"},{"key":"1221_CR28","doi-asserted-by":"publisher","unstructured":"Song, S., Yu, F., Zeng, A., Chang, A. X., Savva, M., & Funkhouser, T. (2017). Semantic scene completion from a single depth image. In 2017 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 190\u2013198), \nhttps:\/\/doi.org\/10.1109\/CVPR.2017.28\n\n.","DOI":"10.1109\/CVPR.2017.28"},{"key":"1221_CR29","doi-asserted-by":"publisher","unstructured":"Sturm, J., Engelhard, N., Endres, F., Burgard, W., & Cremers, D. (2012). A benchmark for the evaluation of RGB-D SLAM systems. In 2012 IEEE\/RSJ international conference on intelligent robots and systems (pp. 573\u2013580), \nhttps:\/\/doi.org\/10.1109\/IROS.2012.6385773\n\n.","DOI":"10.1109\/IROS.2012.6385773"},{"key":"1221_CR30","doi-asserted-by":"publisher","unstructured":"Tateno, K., Tombari, F., Laina, I., & Navab, N. (2017). 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), \nhttps:\/\/doi.org\/10.1109\/CVPR.2017.695\n\n.","DOI":"10.1109\/CVPR.2017.695"},{"key":"1221_CR31","doi-asserted-by":"crossref","unstructured":"Ummenhofer, B., Zhou, H., Uhrig, J., Mayer, N., Ilg, E., Dosovitskiy, A., & Brox, T. (2017). DeMoN: Depth and motion network for learning monocular stereo. In IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.596"},{"key":"1221_CR32","doi-asserted-by":"publisher","unstructured":"Valada, A., Radwan, N., & Burgard, W. (2018). Deep auxiliary learning for visual localization and odometry. In 2018 IEEE international conference on robotics and automation (ICRA) (pp. 6939\u20136946), \nhttps:\/\/doi.org\/10.1109\/ICRA.2018.8462979\n\n.","DOI":"10.1109\/ICRA.2018.8462979"},{"key":"1221_CR33","unstructured":"Vijayanarasimhan, S., Ricco, S., Schmid, C., Sukthankar, R., & Fragkiadaki, K. (2017). SfM-Net: Learning of structure and motion from video. \narXiv:170407804\n\n [cs]."},{"key":"1221_CR34","doi-asserted-by":"publisher","unstructured":"Wang, S., Clark, R., Wen, H., & Trigoni, N. (2017). 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), \nhttps:\/\/doi.org\/10.1109\/ICRA.2017.7989236\n\n.","DOI":"10.1109\/ICRA.2017.7989236"},{"key":"1221_CR35","doi-asserted-by":"publisher","unstructured":"Weerasekera, C. S., Latif, Y., Garg, R., & Reid, I. (2017). Dense monocular reconstruction using surface normals. In 2017 IEEE international conference on robotics and automation (ICRA) (pp. 2524\u20132531), \nhttps:\/\/doi.org\/10.1109\/ICRA.2017.7989293\n\n.","DOI":"10.1109\/ICRA.2017.7989293"},{"key":"1221_CR36","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1007\/978-3-030-20873-8_39","volume-title":"Computer Vision \u2013 ACCV 2018","author":"Chamara Saroj Weerasekera","year":"2019","unstructured":"Weerasekera, C. S., Garg, R., Latif, Y., Reid, I. (2018). Learning deeply supervised good features to match for dense monocular reconstruction. In Computer vision\u2014ACCV 2018 (pp. 609\u2013624). Cham: Springer, \nhttps:\/\/doi.org\/10.1007\/978-3-030-20873-8_39\n\n."},{"key":"1221_CR37","doi-asserted-by":"publisher","unstructured":"Xiao, J., Owens, A., & Torralba, A. (2013). SUN3D: A database of big spaces reconstructed using SfM and object labels. In 2013 IEEE international conference on computer vision (ICCV) (pp. 1625\u20131632), \nhttps:\/\/doi.org\/10.1109\/ICCV.2013.458\n\n.","DOI":"10.1109\/ICCV.2013.458"},{"key":"1221_CR38","doi-asserted-by":"crossref","unstructured":"Zhan, H., Garg, R., Saroj\u00a0Weerasekera, C., Li, K., Agarwal, H., & Reid, I. (2018). Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction. In The IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00043"},{"key":"1221_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, H., & Patel, V. M. (2018a) Densely connected pyramid dehazing network. In CVPR.","DOI":"10.1109\/CVPR.2018.00337"},{"key":"1221_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, H., & Patel, V. M. (2018b) Density-aware single image de-raining using a multi-stream dense network. In CVPR.","DOI":"10.1109\/CVPR.2018.00079"},{"key":"1221_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, H., Ummenhofer, B., & Brox, T. (2018). Deeptam: Deep tracking and mapping. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-01270-0_50"},{"key":"1221_CR42","doi-asserted-by":"publisher","unstructured":"Zhou, T., Brown, M., Snavely, N., & Lowe, D. G. (2017). Unsupervised learning of depth and ego-motion from video. In 2017 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 6612\u20136619), \nhttps:\/\/doi.org\/10.1109\/CVPR.2017.700\n\n.","DOI":"10.1109\/CVPR.2017.700"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-019-01221-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-019-01221-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-019-01221-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T23:14:55Z","timestamp":1599002095000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-019-01221-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,3]]},"references-count":42,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["1221"],"URL":"https:\/\/doi.org\/10.1007\/s11263-019-01221-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2019,9,3]]},"assertion":[{"value":"31 January 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}