{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T18:31:11Z","timestamp":1726511471445},"reference-count":210,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"funder":[{"DOI":"10.13039\/501100007046","name":"Wuhan University","doi-asserted-by":"publisher","award":["CXFW-18-413100063"],"id":[{"id":"10.13039\/501100007046","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61501198"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province, China","doi-asserted-by":"publisher","award":["2014CFB461","2017CFB598"],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Signal Processing: Image Communication"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1016\/j.image.2018.12.002","type":"journal-article","created":{"date-parts":[[2018,12,12]],"date-time":"2018-12-12T08:45:41Z","timestamp":1544604341000},"page":"9-24","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":96,"special_numbering":"C","title":["A survey of variational and CNN-based optical flow techniques"],"prefix":"10.1016","volume":"72","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-4395-6614","authenticated-orcid":false,"given":"Zhigang","family":"Tu","sequence":"first","affiliation":[]},{"given":"Wei","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Dejun","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Ronald","family":"Poppe","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1934-7170","authenticated-orcid":false,"given":"Remco C.","family":"Veltkamp","sequence":"additional","affiliation":[]},{"given":"Baoxin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"1\u20133","key":"10.1016\/j.image.2018.12.002_b1","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/0004-3702(81)90024-2","article-title":"Determining optical flow","volume":"17","author":"Horn","year":"1981","journal-title":"Artif. Intell."},{"key":"10.1016\/j.image.2018.12.002_b2","unstructured":"B. Lucas, T. Kanade, An iterative image registration technique with an application to stereo vision, in: Proc. IJCAI, 1981, pp. 674\u2013679."},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b3","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1109\/TPAMI.2010.143","article-title":"Large displacement optical flow: descriptor matching in variational motion estimation","volume":"33","author":"Brox","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"10.1016\/j.image.2018.12.002_b4","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1007\/BF01420984","article-title":"Performance of optical flow techniques","volume":"12","author":"Barron","year":"1994","journal-title":"Int. J. Comput. Vis."},{"issue":"1","key":"10.1016\/j.image.2018.12.002_b5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11263-010-0390-2","article-title":"A database and evaluation methodology for optical flow","volume":"92","author":"Baker","year":"2011","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2018.12.002_b6","series-title":"Variational Optic Flow Computation: Accurate Modelling and Efficient Numerics","author":"Bruhn","year":"2006"},{"key":"10.1016\/j.image.2018.12.002_b7","series-title":"The Perception of the Visual World","author":"Gibson","year":"1950"},{"key":"10.1016\/j.image.2018.12.002_b8","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1017\/S0033583500002535","article-title":"Visual control orientation behavior in the fly: Part II. Towards underlying neural interactions","volume":"9","author":"Poggio","year":"1976","journal-title":"Q. Rev. Biophys."},{"key":"10.1016\/j.image.2018.12.002_b9","doi-asserted-by":"crossref","unstructured":"I. Kajo, A. Malik, N. Kamel, An evaluation of optical flow algorithms for crowd analytics in surveillance system, in: Proc. Int. Conf. Intelligent and Advanced Systems, 2016, 2016, pp. 1\u20136.","DOI":"10.1109\/ICIAS.2016.7824064"},{"issue":"4","key":"10.1016\/j.image.2018.12.002_b10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1177352.1177355","article-title":"Object tracking: a survey","volume":"38","author":"Yilmaz","year":"2006","journal-title":"ACM Comput. Surv."},{"issue":"6","key":"10.1016\/j.image.2018.12.002_b11","doi-asserted-by":"crossref","first-page":"2752","DOI":"10.1109\/TIP.2016.2554321","article-title":"Text detection, tracking and recognition in video: A comprehensive survey","volume":"25","author":"Xu","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.image.2018.12.002_b12","doi-asserted-by":"crossref","unstructured":"F. Xiao, Y. Lee, Track and segment: An iterative unsupervised approach for video object proposals, in: Proc. CVPR, 2016, pp. 933\u2013942.","DOI":"10.1109\/CVPR.2016.107"},{"key":"10.1016\/j.image.2018.12.002_b13","doi-asserted-by":"crossref","unstructured":"Y. Tsai, M. Yang, M. Black, Video segmentation via object flow, in: Proc. CVPR, 2016, pp. 3899\u20133908.","DOI":"10.1109\/CVPR.2016.423"},{"key":"10.1016\/j.image.2018.12.002_b14","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1016\/j.patcog.2017.07.028","article-title":"Fusing disparate object signatures for salient object detection in video","volume":"72","author":"Tu","year":"2017","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.image.2018.12.002_b15","unstructured":"K. Simonyan, A. Zisserman, Two-stream convolutional networks for action recognition in videos, in: Proc. NIPS, 2014, pp. 568\u2013576."},{"key":"10.1016\/j.image.2018.12.002_b16","doi-asserted-by":"crossref","unstructured":"Z. Tu, J. Cao, Y. Li, B. Li, MSR-CNN: Applying motion salient region based descriptors for action Recognition, in: Proc. ICPR, 2016, pp. 3524\u20133529.","DOI":"10.1109\/ICPR.2016.7900180"},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b17","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1109\/TCSVT.2016.2637778","article-title":"Histograms of optical flow orientation and magnitude and entropy to detect anomalous events in videos","volume":"27","author":"Colque","year":"2017","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.image.2018.12.002_b18","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/j.cviu.2016.10.010","article-title":"Detecting anomalous events in videos by learning deep representations of appearance and motion","volume":"156","author":"Xu","year":"2017","journal-title":"Comput. Vis. Image Underst."},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b19","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1007\/s10846-008-9235-4","article-title":"Visual navigation for mobile robots: A survey","volume":"53","author":"Font","year":"2008","journal-title":"J. Intell. Robot. Syst."},{"issue":"2","key":"10.1016\/j.image.2018.12.002_b20","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1109\/34.982903","article-title":"Vision for mobile robot navigation: A survey","volume":"24","author":"Desouza","year":"2002","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.image.2018.12.002_b21","unstructured":"J. Victor, G. Sandini, F. Curotto, S. Garibaldi, Divergence stereo for robot navigation: Learning from bees, in: Proc. CVPR, 1993, pp. 434\u2013439."},{"key":"10.1016\/j.image.2018.12.002_b22","doi-asserted-by":"crossref","unstructured":"H. Ho, C. Wagter, B. Remes, G. de\u00a0Croon, Optical flow for self-supervised learning of obstacle appearance, in: Proc. Int. Conf. Intell. Robots and Systems, 2015, pp. 3098\u20133104.","DOI":"10.1109\/IROS.2015.7353805"},{"key":"10.1016\/j.image.2018.12.002_b23","series-title":"High-Speed Autonomous Obstacle Avoidance with Pushbroom Stereo","author":"Barry","year":"2016"},{"issue":"2","key":"10.1016\/j.image.2018.12.002_b24","first-page":"380","article-title":"Ultra-high-throughput VLSI architecture of H.265\/HEVC CABAC encoder for UHDTV applications","volume":"27","author":"Zhou","year":"2017","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b25","doi-asserted-by":"crossref","first-page":"1020","DOI":"10.1109\/TIP.2011.2179305","article-title":"Image sequence interpolation based on optical flow, segmentation, and optimal control","volume":"21","author":"Chen","year":"2012","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.image.2018.12.002_b26","doi-asserted-by":"crossref","unstructured":"S. Niklaus, L. Mai, F. Liu, Video frame interpolation via adaptive convolution, in: Proc. CVPR, 2017, pp. 670\u2013679.","DOI":"10.1109\/CVPR.2017.244"},{"key":"10.1016\/j.image.2018.12.002_b27","doi-asserted-by":"crossref","unstructured":"C. Liu, D. Sun, A bayesian approach to adaptive video super resolution, in: Proc. CVPR, 2011, pp. 209\u2013216.","DOI":"10.1109\/CVPR.2011.5995614"},{"key":"10.1016\/j.image.2018.12.002_b28","doi-asserted-by":"crossref","unstructured":"O. Makansi, E. Ilg, T. Brox, End-to-end learning of video super-resolution with motion compensation, in: Proc. GCPR, 2017.","DOI":"10.1007\/978-3-319-66709-6_17"},{"key":"10.1016\/j.image.2018.12.002_b29","doi-asserted-by":"crossref","first-page":"1479","DOI":"10.1175\/2010WAF2222351.1","article-title":"Optical flow for verification","volume":"25","author":"Caren","year":"2010","journal-title":"Weather Forecast."},{"issue":"8","key":"10.1016\/j.image.2018.12.002_b30","doi-asserted-by":"crossref","first-page":"2385","DOI":"10.1109\/TGRS.2008.918167","article-title":"3D motion estimation of atmospheric layers from image sequences","volume":"46","author":"Heas","year":"2008","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"4","key":"10.1016\/j.image.2018.12.002_b31","doi-asserted-by":"crossref","first-page":"36:1","DOI":"10.1145\/3072959.3073662","article-title":"Rainbow particle imaging velocimetry for dense 3D fluid velocity imaging","volume":"36","author":"Xiong","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.image.2018.12.002_b32","first-page":"103","article-title":"A survey on variational optic flow methods for small displacements","volume":"10","author":"Weickert","year":"2006","journal-title":"Math. Models Regist. Appl. Med. Imaging"},{"key":"10.1016\/j.image.2018.12.002_b33","series-title":"Local, semi-Global, and Global Optimization for Motion Estimation","author":"Trobin","year":"2009"},{"key":"10.1016\/j.image.2018.12.002_b34","series-title":"Variational Optical Flow Algorithms for Motion Estimation","author":"Tu","year":"2015"},{"key":"10.1016\/j.image.2018.12.002_b35","doi-asserted-by":"crossref","unstructured":"T. Brox, A. Bruhn, N. Papenberg, J. Weickert, High accuracy optical flow estimation based on a theory for warping, in: Proc. ECCV, 2004, pp. 25\u201336.","DOI":"10.1007\/978-3-540-24673-2_3"},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b36","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1023\/B:VISI.0000045324.43199.43","article-title":"Lucas\/Kanade meets Horn\/Schunck: Combining local and global optic flow methods","volume":"61","author":"Bruhn","year":"2005","journal-title":"Int. J. Comput. Vis."},{"issue":"1","key":"10.1016\/j.image.2018.12.002_b37","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1137\/S0036139998340170","article-title":"Computing optical flow via variational techniques","volume":"60","author":"Aubert","year":"1999","journal-title":"SIAM J. Appl. Math."},{"issue":"1","key":"10.1016\/j.image.2018.12.002_b38","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1006\/cviu.1996.0006","article-title":"The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields","volume":"63","author":"Black","year":"1996","journal-title":"Comput. Vis. Image Underst."},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b39","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1023\/A:1011286029287","article-title":"Variational optic flow computation with a spatio-temporal smoothness constraint","volume":"14","author":"Weickert","year":"2001","journal-title":"J. Math. Imaging Vision"},{"key":"10.1016\/j.image.2018.12.002_b40","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cviu.2015.02.008","article-title":"Optical flow modeling and computation: A survey","volume":"134","author":"Fortun","year":"2015","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.image.2018.12.002_b41","doi-asserted-by":"crossref","unstructured":"Y. Boykov, O. Veksler, R. Zabih, Markov random fields with efficient approximations, in: Proc. CVPR, 1998, pp. 648\u2013655.","DOI":"10.1109\/CVPR.1998.698673"},{"key":"10.1016\/j.image.2018.12.002_b42","doi-asserted-by":"crossref","unstructured":"W. Li, D. Cosker, M. Brown, R. Tang, Optical flow estimation using Laplacian mesh energy, in: Proc. CVPR, 2013, pp. 2435\u20132442.","DOI":"10.1109\/CVPR.2013.315"},{"issue":"5","key":"10.1016\/j.image.2018.12.002_b43","doi-asserted-by":"crossref","first-page":"2044","DOI":"10.1109\/TIP.2013.2244221","article-title":"Constrained optical flow estimation as a matching problem","volume":"22","author":"Mozerov","year":"2013","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.image.2018.12.002_b44","doi-asserted-by":"crossref","unstructured":"M. Hornaek, F. Besse, J. Kautz, A. Fitzgibbon, C. Rother, Highly over parameterized optical flow using patchmatch belief propagation, in: Proc. ECCV, 2014, pp. 220\u2013234.","DOI":"10.1007\/978-3-319-10578-9_15"},{"issue":"1","key":"10.1016\/j.image.2018.12.002_b45","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/s11263-006-0016-x","article-title":"On the spatial statistics of optical flow","volume":"74","author":"Roth","year":"2007","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2018.12.002_b46","doi-asserted-by":"crossref","unstructured":"V. Lempitsky, S. Roth, C. Rother, Fusion flow: Discrete continuous optimization for optical flow estimation, in: Proc. CVPR, 2008, pp. 1\u20138.","DOI":"10.1109\/CVPR.2008.4587751"},{"key":"10.1016\/j.image.2018.12.002_b47","doi-asserted-by":"crossref","unstructured":"M. Menze, C. Heipke, A. Geiger, Discrete optimization for optical flow, in: Proc. GCPR, 2015, pp. 16\u201328.","DOI":"10.1007\/978-3-319-24947-6_2"},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b48","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1007\/s11263-006-6616-7","article-title":"A multigrid platform for real-time motion computation with discontinuity\u2013preserving variational methods","volume":"70","author":"Bruhn","year":"2006","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2018.12.002_b49","doi-asserted-by":"crossref","unstructured":"C. Zach, T. Pock, H. Bischof, A duality based approach for realtime TV-L1 optical flow, in: DAGM conf. PR, 2007, pp. 214\u2013223.","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"10.1016\/j.image.2018.12.002_b50","doi-asserted-by":"crossref","unstructured":"S. Oron, A. Hillel, S. Avidan, Extended lucas-kanade tracking, in: Proc. ECCV, 2014, pp. 142\u2013156.","DOI":"10.1007\/978-3-319-10602-1_10"},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b51","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1023\/B:VISI.0000011205.11775.fd","article-title":"Lucas-Kanade 20 years on: A unifying framework","volume":"56","author":"Baker","year":"2004","journal-title":"Int. J. Comput. Vis."},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b52","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1007\/BF00158167","article-title":"A computational framework and an algorithm for the measurement of visual motion","volume":"2","author":"Anandan","year":"1989","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2018.12.002_b53","series-title":"Fast Normalized Cross-Correlation","first-page":"120","author":"Lewis","year":"1995"},{"key":"10.1016\/j.image.2018.12.002_b54","doi-asserted-by":"crossref","unstructured":"J. Wills, S. Belongie, A feature-based approach for determining dense long range correspondences, in: Proc. ECCV, 2004, pp. 170\u2013182.","DOI":"10.1007\/978-3-540-24672-5_14"},{"issue":"5","key":"10.1016\/j.image.2018.12.002_b55","doi-asserted-by":"crossref","first-page":"1107","DOI":"10.1109\/TPAMI.2012.171","article-title":"Learning a confidence measure for optical flow","volume":"35","author":"Aodha","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"10.1016\/j.image.2018.12.002_b56","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1007\/s11263-006-6660-3","article-title":"A feature-based approach for dense segmentation and estimation of large disparity motion","volume":"68","author":"Wills","year":"2006","journal-title":"Int. J. Comput. Vis."},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b57","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1145\/212094.212141","article-title":"The computation of optical flow","volume":"27","author":"Beauchemin","year":"1995","journal-title":"ACM Comput. Surv."},{"issue":"4","key":"10.1016\/j.image.2018.12.002_b58","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00133568","article-title":"Optical flow using spatiotemporal filters","volume":"1","author":"Heeger","year":"1988","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2018.12.002_b59","series-title":"A Look at Motion in the Frequency Domain","first-page":"1","author":"Watson","year":"1983"},{"issue":"2","key":"10.1016\/j.image.2018.12.002_b60","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1364\/JOSAA.2.000284","article-title":"Spatiotemporal energy models for the perception of motion","volume":"2","author":"Adelson","year":"1985","journal-title":"J. Opt. Soc. Amer."},{"issue":"1","key":"10.1016\/j.image.2018.12.002_b61","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/BF00056772","article-title":"Computation of component image velocity from local phase information","volume":"5","author":"Fleet","year":"1990","journal-title":"Int. J. Comput. Vis."},{"issue":"9","key":"10.1016\/j.image.2018.12.002_b62","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1109\/34.93808","article-title":"The design and use of steerable filters","volume":"13","author":"Freeman","year":"1991","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.image.2018.12.002_b63","doi-asserted-by":"crossref","unstructured":"A. Dosovitskiy, P. Fischer, E. Ilg, P. Hausser, C. Haz\u0131rbas, V. Golkov, P. Smagt, D. Cremers, T. Brox, FlowNet: Learning optical flow with convolutional networks, in: Proc. ICCV, 2015, pp. 2758\u20132766.","DOI":"10.1109\/ICCV.2015.316"},{"key":"10.1016\/j.image.2018.12.002_b64","doi-asserted-by":"crossref","unstructured":"Z. Ren, J. Yan, B. Ni, B. Liu, X. Yang, H. Zha, Unsupervised deep learning for optical flow estimation, in: Proc. AAAI, 2017.","DOI":"10.1609\/aaai.v31i1.10723"},{"key":"10.1016\/j.image.2018.12.002_b65","doi-asserted-by":"crossref","unstructured":"F. Guney, A. Geiger, Deep discrete flow, in: Proc. ACCV, 2016, pp. 207\u2013224.","DOI":"10.1007\/978-3-319-54190-7_13"},{"key":"10.1016\/j.image.2018.12.002_b66","doi-asserted-by":"crossref","unstructured":"S. Zweigand, L. Wolf, InterpoNet, a brain inspired neural network for optical flow dense interpolation, in: Proc. CVPR, 2017, pp. 4563\u20134572.","DOI":"10.1109\/CVPR.2017.674"},{"key":"10.1016\/j.image.2018.12.002_b67","doi-asserted-by":"crossref","unstructured":"E. Ilg, N. Mayer, T. Saikia, M. Keuper, A. Dosovitskiy, T. Brox, FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks, in: Proc. CVPR, 2017, pp. 1647\u20131655.","DOI":"10.1109\/CVPR.2017.179"},{"key":"10.1016\/j.image.2018.12.002_b68","doi-asserted-by":"crossref","unstructured":"M. Otte, H. Nagel, Optical flow estimation: advances and comparisons, in: Proc. ECCV, 1994, pp. 51\u201360.","DOI":"10.1007\/3-540-57956-7_5"},{"key":"10.1016\/j.image.2018.12.002_b69","doi-asserted-by":"crossref","unstructured":"B. Galvin, B. McCane, K. Novins, D. Mason, S. Mills, Recovering motion fields: An Evaluation of eight optical flow algorithms, in: Proc. BMVC, 1998, pp. 195\u2013204.","DOI":"10.5244\/C.12.20"},{"issue":"1","key":"10.1016\/j.image.2018.12.002_b70","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1006\/cviu.2001.0930","article-title":"On benchmarking optical flow","volume":"84","author":"McCane","year":"2001","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.image.2018.12.002_b71","doi-asserted-by":"crossref","unstructured":"R. Szeliski, Prediction error as a quality metric for motion and stereo, in: Proc. ICCV, 1999, pp. 781\u2013788.","DOI":"10.1109\/ICCV.1999.790301"},{"key":"10.1016\/j.image.2018.12.002_b72","doi-asserted-by":"crossref","unstructured":"M. Menze, A. Geiger, Object scene flow for autonomous vehicles, in: Proc. CVPR, 2015, pp. 3061\u20133070.","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"10.1016\/j.image.2018.12.002_b73","doi-asserted-by":"crossref","unstructured":"D. Butler, J.W.G. Stanley, M. Black, A naturalistic open source movie for optical flow evaluation, in: Proc. ECCV, 2012, pp. 611\u2013625.","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"10.1016\/j.image.2018.12.002_b74","doi-asserted-by":"crossref","unstructured":"M. Aubry, D. Maturana, A. Efros, B. Russell, J. Sivic, Seeing 3D chairs: Exemplar part-based 2D\u20133D alignment using a large dataset of CAD models, in: Proc. CVPR, 2014, pp. 3762\u20133769.","DOI":"10.1109\/CVPR.2014.487"},{"key":"10.1016\/j.image.2018.12.002_b75","doi-asserted-by":"crossref","unstructured":"C. Vogel, S. Roth, K. Schindler, An evaluation of data costs for optical flow, in: Proc. GCPR, 2013, pp. 343\u2013353.","DOI":"10.1007\/978-3-642-40602-7_37"},{"key":"10.1016\/j.image.2018.12.002_b76","doi-asserted-by":"crossref","unstructured":"D. Sun, S. Roth, M. Black, Secrets of optical flow estimation and their principles, in: Proc. CVPR, 2010, pp. 2432\u20132439.","DOI":"10.1109\/CVPR.2010.5539939"},{"issue":"9","key":"10.1016\/j.image.2018.12.002_b77","first-page":"1","article-title":"Motion detail preserving optical flow estimation","volume":"34","author":"Xu","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"10.1016\/j.image.2018.12.002_b78","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1109\/TCSVT.2005.861947","article-title":"FPGA-based real-time optical flow system","volume":"16","author":"Diaz","year":"2006","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.image.2018.12.002_b79","doi-asserted-by":"crossref","unstructured":"L. Bao, Q. Yang, H. Jin, Fast edge-preserving patchmatch for large displacement optical flow, in: Proc. CVPR, 2014, pp. 3534\u20133541.","DOI":"10.1109\/CVPR.2014.452"},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b80","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1007\/s11263-007-0041-4","article-title":"Symmetrical dense optical flow estimation with occlusions detection","volume":"75","author":"Alvarez","year":"2007","journal-title":"Int. J. Comput. Vis."},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b81","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1007\/s11263-011-0490-7","article-title":"Sparse occlusion detection with optical flow","volume":"97","author":"Ayvaci","year":"2012","journal-title":"Int. J. Comput. Vis."},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b82","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1007\/s11263-011-0422-6","article-title":"Optic flow in harmony","volume":"93","author":"Zimmer","year":"2011","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2018.12.002_b83","doi-asserted-by":"crossref","unstructured":"Y. Mileva, A. Bruhn, J. Weickert, Illumination-robust variational optical flow with photometric invariants, in: DAGM PR Symposium, 2007, pp. 152\u2013162.","DOI":"10.1007\/978-3-540-74936-3_16"},{"issue":"5","key":"10.1016\/j.image.2018.12.002_b84","article-title":"Estimating accurate optical flow in the presence of motion blur","volume":"24","author":"Tu","year":"2015","journal-title":"J. EI"},{"issue":"2","key":"10.1016\/j.image.2018.12.002_b85","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1007\/s11263-005-3960-y","article-title":"Highly accurate optic flow computation with theoretically justified warping","volume":"67","author":"Papenberg","year":"2006","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2018.12.002_b86","first-page":"235","article-title":"A scale-space approach to nonlocal optical flow calculations","volume":"vol. 1682","author":"Alvarez","year":"1999"},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b87","doi-asserted-by":"crossref","DOI":"10.1117\/1.OE.51.3.037202","article-title":"Weighted root mean square approach to select the optimal smoothness parameter of the variational optical flow algorithms","volume":"51","author":"Tu","year":"2012","journal-title":"Opt. Eng."},{"key":"10.1016\/j.image.2018.12.002_b88","doi-asserted-by":"crossref","unstructured":"H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, H. Seidel, Complementary optic flow, in: Proc. EMMCVPR, 2009, pp. 207\u2013220.","DOI":"10.1007\/978-3-642-03641-5_16"},{"key":"10.1016\/j.image.2018.12.002_b89","unstructured":"J. Weijer, T. Gevers, Robust optical flow from photometric invariants, in: Proc. ICIP, 2004, pp. 1835\u20131838."},{"issue":"9","key":"10.1016\/j.image.2018.12.002_b90","doi-asserted-by":"crossref","first-page":"1499","DOI":"10.1109\/TCSVT.2014.2308628","article-title":"Illumination-Robust optical flow using a local directional pattern","volume":"24","author":"Mohamed","year":"2014","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"1","key":"10.1016\/j.image.2018.12.002_b91","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/s11263-006-4331-z","article-title":"Structure-texture image decomposition-modeling, algorithms, and parameter selection","volume":"67","author":"Aujol","year":"2006","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2018.12.002_b92","first-page":"23","article-title":"An improved algorithm for tv-l1 optical flow","volume":"5064","author":"Wedel","year":"2008","journal-title":"Sta. and Geometrical Appl. to Vis. Motion Anal."},{"key":"10.1016\/j.image.2018.12.002_b93","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/0167-2789(92)90242-F","article-title":"Nonlinear total variation based noise removal algorithms","volume":"60","author":"Rudin","year":"1992","journal-title":"Physica D"},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b94","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1006\/cviu.1997.0553","article-title":"Motion from color","volume":"68","author":"Golland","year":"1997","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.image.2018.12.002_b95","doi-asserted-by":"crossref","unstructured":"M.J. Black, P. Anandan, Robust dynamic motion estimation over time, in: Proc. CVPR, 1991, pp. 292\u2013302.","DOI":"10.1109\/CVPR.1991.139705"},{"key":"10.1016\/j.image.2018.12.002_b96","doi-asserted-by":"crossref","unstructured":"P. Charbonnier, L. Blanc-Feraud, G. Aubert, M. Barlaud, Two deterministic half-quadratic regularization algorithms for computed imaging, in: Proc. ICIP, 1994, pp. 168\u2013172.","DOI":"10.1109\/ICIP.1994.413553"},{"issue":"4","key":"10.1016\/j.image.2018.12.002_b97","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1006\/jvci.1995.1029","article-title":"Robust multiresolution estimation of parametric motion models","volume":"6","author":"Odobez","year":"1995","journal-title":"J. Vis. Commun. Image Represent."},{"issue":"5","key":"10.1016\/j.image.2018.12.002_b98","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1109\/83.668027","article-title":"Dense estimation and object-based segmentation of the optical flow with robust techniques","volume":"7","author":"Memin","year":"1998","journal-title":"IEEE Trans. Image Process."},{"issue":"9","key":"10.1016\/j.image.2018.12.002_b99","doi-asserted-by":"crossref","first-page":"1377","DOI":"10.1109\/TCSVT.2012.2202070","article-title":"Robust local optical flow for feature tracking","volume":"22","author":"Senst","year":"2012","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"2","key":"10.1016\/j.image.2018.12.002_b100","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/s11263-013-0644-x","article-title":"A quantitative analysis of current practices in optical flow estimation and the principles behind them","volume":"106","author":"Sun","year":"2014","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2018.12.002_b101","series-title":"Visual Reconstruction","author":"Blake","year":"1987"},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b102","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1023\/A:1013614317973","article-title":"A theoretical framework for convex regularizers in PDE-based computation of image motion","volume":"45","author":"Weickert","year":"2001","journal-title":"Int. J. Comput. Vis."},{"issue":"1","key":"10.1016\/j.image.2018.12.002_b103","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1008170101536","article-title":"Reliable estimation of dense optical flow fields with large displacements","volume":"39","author":"Alvarez","year":"2000","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2018.12.002_b104","doi-asserted-by":"crossref","unstructured":"C. Schnorr, Segmentation of visual motion by minimizing convex non-quadratic functionals, in: Proc. ICPR, 1994, pp. 661\u2013663.","DOI":"10.1109\/ICPR.1994.576391"},{"key":"10.1016\/j.image.2018.12.002_b105","doi-asserted-by":"crossref","unstructured":"M. Werlberger, T. Pock, H. Bischof, Motion estimation with non-local total variation regularization, in: Proc. ICCV, 2010, pp. 2464\u20132471.","DOI":"10.1109\/CVPR.2010.5539945"},{"key":"10.1016\/j.image.2018.12.002_b106","doi-asserted-by":"crossref","unstructured":"P. Krahenbuhl, V. Koltun, Efficient nonlocal regularization for optical flow, in: Proc. ECCV, 2012, pp. 356\u2013369.","DOI":"10.1007\/978-3-642-33718-5_26"},{"key":"10.1016\/j.image.2018.12.002_b107","doi-asserted-by":"crossref","unstructured":"S. Volz, A. Bruhn, L. Valgaerts, H. Zimmer, Modeling temporal coherence for optical flow, in: Proc. ICCV, 2011, pp. 1116\u20131123.","DOI":"10.1109\/ICCV.2011.6126359"},{"key":"10.1016\/j.image.2018.12.002_b108","doi-asserted-by":"crossref","unstructured":"R. Garg, A. Roussos, L. Agapito, Robust trajectory-space TV-L1 optical flow for non-rigid sequences, in: Proc. EMMCVPR, 2011, pp. 300\u2013314.","DOI":"10.1007\/978-3-642-23094-3_22"},{"issue":"5","key":"10.1016\/j.image.2018.12.002_b109","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1109\/TPAMI.1986.4767833","article-title":"An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences","volume":"8","author":"Nagel","year":"1986","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.image.2018.12.002_b110","doi-asserted-by":"crossref","unstructured":"V. Solo, A sure-fired way to choose smoothing parameters in ill-conditioned inverse problems, in: Proc. ICIP, 1996, pp. 89\u201392.","DOI":"10.1109\/ICIP.1996.560376"},{"key":"10.1016\/j.image.2018.12.002_b111","doi-asserted-by":"crossref","unstructured":"L. Ng, V. Solo, A data-driven method for choosing smoothing parameters in optical flow problems, in: Proc. ICIP, 1997, pp. 360\u2013363.","DOI":"10.1109\/ICIP.1997.632117"},{"key":"10.1016\/j.image.2018.12.002_b112","doi-asserted-by":"crossref","unstructured":"L. Raket, Local smoothness for global optical flow, in: Proc. ICIP, 2012, pp. 1\u20134.","DOI":"10.1109\/ICIP.2012.6674231"},{"key":"10.1016\/j.image.2018.12.002_b113","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/j.patcog.2015.09.002","article-title":"Weighted local intensity fusion method for variational optical flow estimation","volume":"50","author":"Tu","year":"2016","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.image.2018.12.002_b114","doi-asserted-by":"crossref","unstructured":"D. Sun, E. Sudderth, H. Pfister, Layered RGBD scene flow estimation, in: Proc. CVPR, 2015, pp. 548\u2013556.","DOI":"10.1109\/CVPR.2015.7298653"},{"key":"10.1016\/j.image.2018.12.002_b115","unstructured":"J. Rua, T. Crivelli, P. Bouthemy, P. Perez, Determining occlusions from space and time image reconstructions, in: Proc. CVPR, 2016, pp. 1382\u20131391."},{"issue":"2","key":"10.1016\/j.image.2018.12.002_b116","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/s10851-015-0596-6","article-title":"Detecting occlusions as an inverse problem","volume":"54","author":"Estellers","year":"2015","journal-title":"J. Math. Imaging Vision"},{"key":"10.1016\/j.image.2018.12.002_b117","doi-asserted-by":"crossref","unstructured":"J. Xiao, H. Cheng, H. Sawhney, C. Rao, M. Isnardi, Bilateral filtering\u2013based optical flow estimation with occlusion detection, in: Proc. ECCV, 2006, pp. 211\u2013224.","DOI":"10.1007\/11744023_17"},{"key":"10.1016\/j.image.2018.12.002_b118","doi-asserted-by":"crossref","unstructured":"D. Sun, S. Roth, J. Lewis, J. Black, Learning optical flow, in: Proc. ECCV, 2008, pp. 83\u201397.","DOI":"10.1007\/978-3-540-88690-7_7"},{"issue":"7","key":"10.1016\/j.image.2018.12.002_b119","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1109\/34.865184","article-title":"A cooperative algorithm for stereo matching and occlusion detection","volume":"22","author":"Zitnick","year":"2000","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"8","key":"10.1016\/j.image.2018.12.002_b120","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.1109\/TIP.2008.925381","article-title":"Occlusion-aware optical flow estimation","volume":"17","author":"Ince","year":"2008","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"10.1016\/j.image.2018.12.002_b121","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1007\/s11263-008-0136-6","article-title":"Particle video: Long-range motion estimation using point trajectories","volume":"80","author":"Sand","year":"2008","journal-title":"Int. J. Comput. Vis."},{"issue":"4","key":"10.1016\/j.image.2018.12.002_b122","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1109\/TPAMI.2004.1265863","article-title":"Layered motion segmentation and depth ordering by tracking edges","volume":"26","author":"Smith","year":"2004","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b123","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1007\/s11263-008-0203-z","article-title":"Occlusion boundaries from motion: Low-level detection and mid-level reasoning","volume":"82","author":"Stein","year":"2009","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2018.12.002_b124","doi-asserted-by":"crossref","unstructured":"P. Sundberg, T. Brox, M. Maire, P. Arbelaez, J. Malik, Occlusion boundary detection and figure\/ground assignment from optical flow, in: Proc. CVPR, 2011, pp. 2233\u20132240.","DOI":"10.1109\/CVPR.2011.5995364"},{"key":"10.1016\/j.image.2018.12.002_b125","doi-asserted-by":"crossref","unstructured":"A. Humayun, O. Aodha, G. Brostow, Learning to find occlusion regions, in: Proc. CVPR, 2011, pp. 2161\u20132168.","DOI":"10.1109\/CVPR.2011.5995517"},{"key":"10.1016\/j.image.2018.12.002_b126","doi-asserted-by":"crossref","unstructured":"C. Kondermann, R. Mester, C. Garbe, A statistical confidence measure for optical flows, in: Proc. ECCV, 2008, pp. 290\u2013301.","DOI":"10.1007\/978-3-540-88690-7_22"},{"issue":"9","key":"10.1016\/j.image.2018.12.002_b127","doi-asserted-by":"crossref","first-page":"2615","DOI":"10.1109\/TIP.2011.2121081","article-title":"Occlusion-aware motion layer extraction under large interframe motions","volume":"20","author":"Xu","year":"2011","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.image.2018.12.002_b128","unstructured":"D. Sun, E. Sudderth, M. Black, Layered segmentation and optical flow estimation over time, in: Proc. CVPR, 2012, pp. 1768\u20131775."},{"key":"10.1016\/j.image.2018.12.002_b129","doi-asserted-by":"crossref","unstructured":"E. Lobaton, R. Vasudevan, R. Bajcsy, R. Alterovitz, Local occlusion detection under deformations using topological invariants, in: Proc. ECCV, 2010, pp. 101\u2013114.","DOI":"10.1007\/978-3-642-15558-1_8"},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b130","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1023\/A:1008026031844","article-title":"Exploiting discontinuities in optical flow","volume":"30","author":"Thompson","year":"1998","journal-title":"Int. J. Comput. Vis."},{"issue":"8","key":"10.1016\/j.image.2018.12.002_b131","doi-asserted-by":"crossref","first-page":"4055","DOI":"10.1109\/TIP.2017.2712279","article-title":"Robust non-local TV-L1 optical flow estimation with occlusion detection","volume":"26","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.image.2018.12.002_b132","doi-asserted-by":"crossref","unstructured":"X. Shen, Y. Wu, Sparsity model for robust optical flow estimation at motion discontinuities, in: Proc. CVPR, 2010, pp. 2456\u20132463.","DOI":"10.1109\/CVPR.2010.5539944"},{"key":"10.1016\/j.image.2018.12.002_b133","doi-asserted-by":"crossref","unstructured":"K. Jia, X. Wang, X. Tang, Optical flow estimation using learned sparse model, in: Proc. ICCV, 2011, pp. 2391\u20132398.","DOI":"10.1109\/ICCV.2011.6126522"},{"issue":"2","key":"10.1016\/j.image.2018.12.002_b134","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1023\/A:1013539930159","article-title":"Hierarchical estimation and segmentation of dense motion fields","volume":"46","author":"Memin","year":"2002","journal-title":"Int. J. Comput. Vis."},{"issue":"2","key":"10.1016\/j.image.2018.12.002_b135","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/s11263-005-6206-0","article-title":"Piecewise-smooth dense optical flow via level sets","volume":"68","author":"Amiaz","year":"2006","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2018.12.002_b136","doi-asserted-by":"crossref","unstructured":"L. Xu, J. Chen, J. Jia, A segmentation based variational model for accurate optical flow estimation, in: Proc. ECCV, 2008, pp. 671\u2013684.","DOI":"10.1007\/978-3-540-88682-2_51"},{"key":"10.1016\/j.image.2018.12.002_b137","unstructured":"L. Lara, D. Sun, V. Jampani, M. Black, Optical flow with semantic segmentation and localized layers, in: Proc. CVPR, 2016, pp. 3889\u20133898."},{"key":"10.1016\/j.image.2018.12.002_b138","doi-asserted-by":"crossref","unstructured":"F. Steinbrucker, T. Pock, Large displacement optical flow computation without warping, in: Proc. CVPR, 2009, pp. 1069\u20131074.","DOI":"10.1109\/ICCV.2009.5459364"},{"key":"10.1016\/j.image.2018.12.002_b139","doi-asserted-by":"crossref","unstructured":"Z. Chen, H. Jin, Z. Lin, S. Cohen, Y. Wu, Large displacement optical flow from nearest neighbor fields, in: Proc. CVPR, 2013, pp. 2443\u20132450.","DOI":"10.1109\/CVPR.2013.316"},{"issue":"5","key":"10.1016\/j.image.2018.12.002_b140","doi-asserted-by":"crossref","first-page":"1926","DOI":"10.1016\/j.patcog.2013.11.026","article-title":"A combined post-filtering method to improve accuracy of variational optical flow estimation","volume":"47","author":"Tu","year":"2014","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.image.2018.12.002_b141","series-title":"Measuring Vision Motion from Image Sequence","author":"Anandan","year":"1987"},{"issue":"5","key":"10.1016\/j.image.2018.12.002_b142","doi-asserted-by":"crossref","first-page":"608","DOI":"10.1109\/TIP.2005.846018","article-title":"Variational optical flow computation in real time","volume":"14","author":"Bruhn","year":"2005","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.image.2018.12.002_b143","doi-asserted-by":"crossref","unstructured":"Y. Yang, S. Soatto, S2F: Slow-To-Fast Interpolator Flow, in: Proc. CVPR, 2017, pp. 2087\u20132096.","DOI":"10.1109\/CVPR.2017.401"},{"issue":"5","key":"10.1016\/j.image.2018.12.002_b144","doi-asserted-by":"crossref","first-page":"978","DOI":"10.1109\/TPAMI.2010.147","article-title":"SIFT flow: Dense correspondence across different scenes and its applications","volume":"33","author":"Liu","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.image.2018.12.002_b145","doi-asserted-by":"crossref","unstructured":"D. Lowe, Object recognition from local scale-invariant features, in: Proc. ICCV, 1999, pp. 1150\u20131157.","DOI":"10.1109\/ICCV.1999.790410"},{"key":"10.1016\/j.image.2018.12.002_b146","doi-asserted-by":"crossref","unstructured":"P. Weinzaepfel, J. Revaud, Z. Harchaoui, C. Schmid, DeepFlow: Large displacement optical flow with deep matching, in: Proc. ICCV, 2013, pp. 1385\u20131392.","DOI":"10.1109\/ICCV.2013.175"},{"issue":"12","key":"10.1016\/j.image.2018.12.002_b147","doi-asserted-by":"crossref","first-page":"4087","DOI":"10.1109\/TGRS.2007.906156","article-title":"Layered estimation of atmospheric mesoscale dynamics from satellite imagery","volume":"45","author":"Heas","year":"2007","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.image.2018.12.002_b148","doi-asserted-by":"crossref","unstructured":"M. Stoll, S. Volz, A. Bruhn, Adaptive integration of feature matches into variational optical flow methods, in: Proc. ACCV, 2012, pp. 1\u201314.","DOI":"10.1007\/978-3-642-37431-9_1"},{"key":"10.1016\/j.image.2018.12.002_b149","unstructured":"J. Zin, R. Dupont, A. Bartoli, A general dense image matching framework combining direct and feature-based costs, in: Proc. ICCV, 2013, pp. 185\u2013192."},{"issue":"5","key":"10.1016\/j.image.2018.12.002_b150","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1016\/j.patcog.2008.08.035","article-title":"MSLD: A robust descriptor for line matching","volume":"42","author":"Wang","year":"2009","journal-title":"Pattern Recognit"},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b151","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1007\/s11263-016-0908-3","article-title":"DeepMatching: hierarchical deformable dense matching","volume":"120","author":"Revaud","year":"2016","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2018.12.002_b152","doi-asserted-by":"crossref","unstructured":"T. Kroeger, R. Timofte, D. Dai, L. Gool, Fast optical flow using dense inverse search, in: Proc. ECCV, 2016, pp. 471\u2013488.","DOI":"10.1007\/978-3-319-46493-0_29"},{"key":"10.1016\/j.image.2018.12.002_b153","doi-asserted-by":"crossref","unstructured":"C. Barnes, E. Shechtman, D. Goldman, A. Finkelstein, The generalized patchmatch correspondence algorithm, in: Proc. ECCV, 2010, pp. 29\u201343.","DOI":"10.1007\/978-3-642-15558-1_3"},{"key":"10.1016\/j.image.2018.12.002_b154","doi-asserted-by":"crossref","unstructured":"J. Revaud, P. Weinzaepfel, Z. Harchaoui, C. Schmid, EpicFlow: Edge-preserving interpolation of correspondences for optical flow, in: Proc. CVPR, 2015, pp. 1164\u20131172.","DOI":"10.1109\/CVPR.2015.7298720"},{"key":"10.1016\/j.image.2018.12.002_b155","doi-asserted-by":"crossref","unstructured":"Y. Hu, Y. Li, R. Song, Robust interpolation of correspondences for large displacement optical flow, in: Proc. CVPR, 2017, pp. 481\u2013489.","DOI":"10.1109\/CVPR.2017.509"},{"key":"10.1016\/j.image.2018.12.002_b156","unstructured":"Y. Li, Pyramidal gradient matching for optical flow estimation, arXiv preprint, 2017, arXiv:1704.03217."},{"issue":"9","key":"10.1016\/j.image.2018.12.002_b157","doi-asserted-by":"crossref","first-page":"1866","DOI":"10.1109\/TPAMI.2016.2616391","article-title":"PatchMatch filter: Edge-aware filtering meets randomized search for visual correspondence","volume":"39","author":"Lu","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.image.2018.12.002_b158","doi-asserted-by":"crossref","unstructured":"C. Bailer, B. Taetz, D. Stricker, Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation, in: Proc. ICCV, 2015, pp. 4015\u20134023.","DOI":"10.1109\/ICCV.2015.457"},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b159","doi-asserted-by":"crossref","first-page":"24:1","DOI":"10.1145\/1531326.1531330","article-title":"PatchMatch: A randomized correspondence algorithm for structural image editing","volume":"28","author":"Barnes","year":"2009","journal-title":"ACM Trans. on Graphics"},{"key":"10.1016\/j.image.2018.12.002_b160","doi-asserted-by":"crossref","unstructured":"Y. Hu, R. Song, Y. Li, Efficient coarse-to-fine patchmatch for large displacement optical flow, in: Proc. CVPR, 2016, pp. 5704\u20135712.","DOI":"10.1109\/CVPR.2016.615"},{"key":"10.1016\/j.image.2018.12.002_b161","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1007\/BF02612354","article-title":"Roof duality, complementation and persistency in quadratic 0-1 optimization","volume":"28","author":"Hammer","year":"1984","journal-title":"Math. Program."},{"key":"10.1016\/j.image.2018.12.002_b162","doi-asserted-by":"crossref","unstructured":"C. Rother, V. Kolmogorov, V. Lempitsky, M. Szummer, Optimizing binary MRFs via extended roof duality, in: Proc. CVPR, 2007, pp. 1\u20138.","DOI":"10.1109\/CVPR.2007.383203"},{"issue":"1","key":"10.1016\/j.image.2018.12.002_b163","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1006\/cviu.2000.0900","article-title":"The statistics of optical flow","volume":"82","author":"Fermuller","year":"2001","journal-title":"Comput. Vis. Image Underst."},{"issue":"6","key":"10.1016\/j.image.2018.12.002_b164","doi-asserted-by":"crossref","first-page":"2128","DOI":"10.1109\/TIP.2013.2246174","article-title":"Quantification of Smoothing Requirement for 3D optic flow calculation of volumetric images","volume":"22","author":"Hadiashar","year":"2013","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"10.1016\/j.image.2018.12.002_b165","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1007\/BF01421489","article-title":"Robust computation of optical flow in a multi-scale differential framework","volume":"14","author":"Weber","year":"1995","journal-title":"Int. J. Comput. Vis."},{"issue":"8","key":"10.1016\/j.image.2018.12.002_b166","doi-asserted-by":"crossref","first-page":"1392","DOI":"10.1109\/TPAMI.2009.143","article-title":"Fusion moves for Markov random field optimization","volume":"32","author":"Lempitsky","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"10.1016\/j.image.2018.12.002_b167","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1109\/TMECH.2010.2046421","article-title":"A Kalman filter-integrated optical flow method for velocity sensing of mobile robots","volume":"16","author":"Song","year":"2011","journal-title":"IEEE Trans. Mechatronics"},{"issue":"6","key":"10.1016\/j.image.2018.12.002_b168","doi-asserted-by":"crossref","first-page":"1397","DOI":"10.1109\/TPAMI.2012.213","article-title":"Guided image filtering","volume":"35","author":"He","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.image.2018.12.002_b169","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.sigpro.2016.02.018","article-title":"Adaptive guided image filter for warping in variational optical flow","volume":"127","author":"Tu","year":"2016","journal-title":"Signal Proc."},{"key":"10.1016\/j.image.2018.12.002_b170","doi-asserted-by":"crossref","unstructured":"A. Buades, B. Coll, J. Morel, A non-local algorithm for image denoising, in: Proc. CVPR, 2005, pp. 60\u201365.","DOI":"10.1109\/CVPR.2005.38"},{"key":"10.1016\/j.image.2018.12.002_b171","doi-asserted-by":"crossref","unstructured":"C. Liu, W. Freeman, A high-quality video denoising algorithm based on reliable motion estimation, in: Proc. ECCV, 2010, pp. 706\u2013719.","DOI":"10.1007\/978-3-642-15558-1_51"},{"key":"10.1016\/j.image.2018.12.002_b172","doi-asserted-by":"crossref","unstructured":"A. Wedel, D. Cremers, T. Pock, H. Bischof, Structure- and motion-adaptive regularization for high accuracy optic flow, in: Proc. ICCV, 2009, pp. 1663\u20131668.","DOI":"10.1109\/ICCV.2009.5459375"},{"key":"10.1016\/j.image.2018.12.002_b173","doi-asserted-by":"crossref","unstructured":"Z. Tu, C. van Gemeren, R.C. Veltkamp, Improved color patch similarity measure based weighted median filter, in: Proc. ACCV, 2015, pp. 1\u201315.","DOI":"10.1007\/978-3-319-16814-2_27"},{"key":"10.1016\/j.image.2018.12.002_b174","doi-asserted-by":"crossref","unstructured":"C. Tomasi, R. Manduchi, Bilateral filtering for gray and color images, in: Proc. ICCV, 1998, pp. 839\u2013846.","DOI":"10.1109\/ICCV.1998.710815"},{"issue":"2","key":"10.1016\/j.image.2018.12.002_b175","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1006\/jvci.1998.0382","article-title":"Recursive optical flow estimation-adaptive filtering approach","volume":"9","author":"Elad","year":"1998","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.image.2018.12.002_b176","doi-asserted-by":"crossref","unstructured":"C. Rabe, T. Muller, A. Wedel, U. Franke, Dense, robust and accurate motion field estimation from stereo image sequences in real-time, in: Proc. ECCV, 2010, pp. 582\u2013595.","DOI":"10.1007\/978-3-642-15561-1_42"},{"key":"10.1016\/j.image.2018.12.002_b177","doi-asserted-by":"crossref","unstructured":"T. Portz, L. Zhang, H. Jiang, Optical flow in the presence of spatially-varying motion blur, in: Proc. CVPR, 2012, pp. 1752\u20131759.","DOI":"10.1109\/CVPR.2012.6247871"},{"key":"10.1016\/j.image.2018.12.002_b178","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.patcog.2016.10.027","article-title":"Variational method for joint optical flow estimation and edge-aware image restoration","volume":"65","author":"Tu","year":"2017","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.image.2018.12.002_b179","doi-asserted-by":"crossref","unstructured":"J. Xu, R. Ranftl, V. Koltun, Accurate optical flow via direct cost volume processing, in: Proc. CVPR, 2017, pp. 1289\u20131297.","DOI":"10.1109\/CVPR.2017.615"},{"key":"10.1016\/j.image.2018.12.002_b180","doi-asserted-by":"crossref","unstructured":"W. Trobin, T. Pock, D. Cremers, H. Bischof, An unbiased second-order prior for high-accuracy motion estimation, in: DAGM Symposium on PR, 2008, pp. 396\u2013405.","DOI":"10.1007\/978-3-540-69321-5_40"},{"key":"10.1016\/j.image.2018.12.002_b181","doi-asserted-by":"crossref","unstructured":"T. Muller, J. Rannacher, C. Rabe, U. Franke, Feature-and depth-supported modified total variation optical flow for 3D motion field estimation in real scenes, in: Proc. CVPR, 2011, pp. 1193\u20131200.","DOI":"10.1109\/CVPR.2011.5995633"},{"key":"10.1016\/j.image.2018.12.002_b182","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/s10851-016-0688-y","article-title":"A new minimization strategy for large displacement variational optical flow","volume":"58","author":"Palomares","year":"2017","journal-title":"J. Math. Imaging Vision"},{"key":"10.1016\/j.image.2018.12.002_b183","series-title":"OPtical Flow Estimation in the Presence of Fast or Discontinuous Motion","author":"Niu","year":"2010"},{"key":"10.1016\/j.image.2018.12.002_b184","series-title":"Applied mathematical sciences","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-44588-5","article-title":"Mathematical problems in image processing: Partial differential equations and the calculus of variations","author":"Aubert","year":"2006"},{"key":"10.1016\/j.image.2018.12.002_b185","doi-asserted-by":"crossref","unstructured":"H. Ho, R. Goecke, Optical flow estimation using Fourier Mellin Transform, in: Proc. CVPR, 2008, pp. 1\u20138.","DOI":"10.1109\/IVS.2007.4290156"},{"issue":"4","key":"10.1016\/j.image.2018.12.002_b186","doi-asserted-by":"crossref","first-page":"1573","DOI":"10.1109\/TIP.2011.2177847","article-title":"Locally oriented optical flow computation","volume":"21","author":"Niu","year":"2012","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.image.2018.12.002_b187","unstructured":"W. Qiu, X. Wang, X. Bai, A. Yuille, Z. Tu, Scale-space SIFT flow, in: Proc. WACV, 2014, pp. 1112\u20131119."},{"issue":"1","key":"10.1016\/j.image.2018.12.002_b188","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3390\/jimaging3010012","article-title":"Dense descriptors for optical flow estimation: A comparative study","volume":"3","author":"Baghaie","year":"2017","journal-title":"J. Imaging"},{"key":"10.1016\/j.image.2018.12.002_b189","doi-asserted-by":"crossref","unstructured":"S. Meister, J. Hur, S. Roth, Unflow: unsupervised learning of optical flow with a bidirectional census loss, in: Proc. AAAI, 2018.","DOI":"10.1609\/aaai.v32i1.12276"},{"key":"10.1016\/j.image.2018.12.002_b190","doi-asserted-by":"crossref","unstructured":"E. Ilg, O. Cicek, S. Galesso, A. Klein, O. Makansi, F. Hutter, T. Brox, Uncertainty estimates and multi-hypotheses networks for optical flow, in: Proc. ECCV, 2018, pp. 652\u2013667.","DOI":"10.1007\/978-3-030-01234-2_40"},{"key":"10.1016\/j.image.2018.12.002_b191","doi-asserted-by":"crossref","unstructured":"N. Mayer, P.H. E.\u00a0Ilg, P. Fischer, D. Cremers, A. Dosovitskiy, T. Brox, A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation, in: Proc. CVPR, 2016, pp. 4040\u20134048.","DOI":"10.1109\/CVPR.2016.438"},{"key":"10.1016\/j.image.2018.12.002_b192","doi-asserted-by":"crossref","first-page":"43222","DOI":"10.1109\/ACCESS.2018.2863233","article-title":"Deep optical flow supervised learning with prior assumptions","volume":"6","author":"Xiang","year":"2018","journal-title":"IEEE Access"},{"key":"10.1016\/j.image.2018.12.002_b193","doi-asserted-by":"crossref","unstructured":"A. Ranjan, M. Black, Optical flow estimation using a spatial pyramid network, in: Proc. CVPR, 2017, pp. 4161\u20134170.","DOI":"10.1109\/CVPR.2017.291"},{"key":"10.1016\/j.image.2018.12.002_b194","doi-asserted-by":"crossref","unstructured":"D. Sun, X. Yang, M. Liu, J. Kautz, PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume, in: Proc. CVPR, 2018, pp. 8934\u20138943.","DOI":"10.1109\/CVPR.2018.00931"},{"key":"10.1016\/j.image.2018.12.002_b195","doi-asserted-by":"crossref","unstructured":"T. Hui, X. Tang, C. Loy, Liteflownet: A lightweight convolutional neural network for optical flow estimation, in: Proc. CVPR, 2018, pp. 8981\u20138989.","DOI":"10.1109\/CVPR.2018.00936"},{"key":"10.1016\/j.image.2018.12.002_b196","doi-asserted-by":"crossref","unstructured":"S. Zhao, L. X, O. Bourahla, Deep optical flow estimation via multi-scale correspondence structure learning, in: Proc. IJCAI, 2017.","DOI":"10.24963\/ijcai.2017\/488"},{"key":"10.1016\/j.image.2018.12.002_b197","doi-asserted-by":"crossref","unstructured":"D. Gadot, L. Wolf, PatchBatch: A batch augmented loss for optical flow, in: Proc. CVPR, 2016, pp. 4236\u20134245.","DOI":"10.1109\/CVPR.2016.459"},{"key":"10.1016\/j.image.2018.12.002_b198","doi-asserted-by":"crossref","unstructured":"T. Schuster, L. Wolf, D. Gadot, Optical flow requires multiple strategies (but only one network), in: Proc. CVPR, 2017, pp. 4950\u20134959.","DOI":"10.1109\/CVPR.2017.732"},{"key":"10.1016\/j.image.2018.12.002_b199","doi-asserted-by":"crossref","unstructured":"M. Bai, W. Luo, K. Kundu, R. Urtasun, Exploiting semantic information and deep matching for optical flow, in: Proc. ECCV, 2016, pp. 154\u2013170.","DOI":"10.1007\/978-3-319-46466-4_10"},{"key":"10.1016\/j.image.2018.12.002_b200","doi-asserted-by":"crossref","unstructured":"C. Bailer, K. Varanasi, D. Stricker, CNN-based patch matching for optical flow with thresholded hinge embedding loss, in: Proc. CVPR, 2017, pp. 3250\u20133259.","DOI":"10.1109\/CVPR.2017.290"},{"issue":"10","key":"10.1016\/j.image.2018.12.002_b201","doi-asserted-by":"crossref","first-page":"2814","DOI":"10.1109\/TMM.2018.2815784","article-title":"Recurrent spatial pyramid cnn for optical flow estimation","volume":"20","author":"Hu","year":"2018","journal-title":"IEEE Trans. Multimedia"},{"key":"10.1016\/j.image.2018.12.002_b202","doi-asserted-by":"crossref","unstructured":"A. Ahmadi, I. Patras, Unsupervised convolutional neural networks for motion estimation, in: Proc. ICIP, 2016, pp. 1629\u20131633.","DOI":"10.1109\/ICIP.2016.7532634"},{"key":"10.1016\/j.image.2018.12.002_b203","doi-asserted-by":"crossref","unstructured":"J.J. Yu, A.W. Harley, K.G. Derpanis, Back to basics: unsupervised learning of optical flow via brightness constancy and motion smoothness, in: Proc. ECCVW, 2016, pp. 3\u201310.","DOI":"10.1007\/978-3-319-49409-8_1"},{"key":"10.1016\/j.image.2018.12.002_b204","unstructured":"Y. Zhu, Z. Lan, S. Newsamy, A. Hauptmann, Guided optical flow learning, in: Proc. CVPRW, 2017."},{"key":"10.1016\/j.image.2018.12.002_b205","unstructured":"M. Jaderberg, K. Simonyan, A. Zisserman, K. Kavukcuoglu, Spatial transformer networks, in: Proc. NIPS, 2015, pp. 2017\u20132025."},{"key":"10.1016\/j.image.2018.12.002_b206","doi-asserted-by":"crossref","unstructured":"L. Fan, W. Huang, C. Gan, S. Ermon, B. Gong, J. Huang, End-to-end learning of motion representation for video understanding, in: Proc. CVPR, 2018, pp. 6016\u20136025.","DOI":"10.1109\/CVPR.2018.00630"},{"key":"10.1016\/j.image.2018.12.002_b207","doi-asserted-by":"crossref","unstructured":"Y. Wang, Y. Yang, Z. Yang, L. Zhao, P. Wang, W. Xu, Occlusion aware unsupervised learning of optical flow, in: Proc. CVPR, 2018, pp. 4884\u20134893.","DOI":"10.1109\/CVPR.2018.00513"},{"key":"10.1016\/j.image.2018.12.002_b208","doi-asserted-by":"crossref","unstructured":"M. Caron, P. Bojanowski, A. Joulin, M. Douze, Deep clustering for unsupervised learning of visual features, in: Proc. ECCV, 2018, pp. 132\u2013149.","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"10.1016\/j.image.2018.12.002_b209","unstructured":"W. Lai, J. Huang, M. Yang, Semi-supervised learning for optical flow with generative adversarial networks, in: Proc. NIPS, 2017."},{"key":"10.1016\/j.image.2018.12.002_b210","doi-asserted-by":"crossref","unstructured":"Y. Yang, S. Soatto, Conditional prior networks for optical flow, in: Proc. ECCV, 2018, pp. 271\u2013287.","DOI":"10.1007\/978-3-030-01267-0_17"}],"container-title":["Signal Processing: Image Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0923596518302479?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0923596518302479?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T01:40:29Z","timestamp":1662601229000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0923596518302479"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3]]},"references-count":210,"alternative-id":["S0923596518302479"],"URL":"https:\/\/doi.org\/10.1016\/j.image.2018.12.002","relation":{},"ISSN":["0923-5965"],"issn-type":[{"value":"0923-5965","type":"print"}],"subject":[],"published":{"date-parts":[[2019,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A survey of variational and CNN-based optical flow techniques","name":"articletitle","label":"Article Title"},{"value":"Signal Processing: Image Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.image.2018.12.002","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2018 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}]}}