{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T13:20:33Z","timestamp":1788528033916,"version":"build-2803163510"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003453","name":"Guangdong Provincial Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114425","type":"journal-article","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T14:51:58Z","timestamp":1783781518000},"page":"114425","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["Shape-aware unsupervised optical flow via multi-scale recurrent refinement and texture-aware loss"],"prefix":"10.1016","volume":"180","author":[{"given":"Ziyang","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7557-9526","authenticated-orcid":false,"given":"Zemin","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanhong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian-huang","family":"Lai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dagang","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1\u20133","key":"10.1016\/j.patcog.2026.114425_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":"Artificial Intelligence"},{"key":"10.1016\/j.patcog.2026.114425_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111789","article-title":"A memory-augmented multi-task collaborative framework for unsupervised traffic anomaly detection in driving videos","volume":"168","author":"Liang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114425_b3","doi-asserted-by":"crossref","unstructured":"Alexey Dosovitskiy, Philipp Fischer, Eddy Ilg, Philip Hausser, Caner Hazirbas, Vladimir Golkov, Patrick Van Der Smagt, Daniel Cremers, Thomas Brox, FlowNet: Learning optical flow with convolutional networks, in: IEEE International Conference on Computer Vision, 2015, pp. 2758\u20132766.","DOI":"10.1109\/ICCV.2015.316"},{"key":"10.1016\/j.patcog.2026.114425_b4","doi-asserted-by":"crossref","unstructured":"Deqing Sun, Xiaodong Yang, Ming-Yu Liu, Jan Kautz, PWC-Net: Cnns for optical flow using pyramid, warping, and cost volume, in: IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8934\u20138943.","DOI":"10.1109\/CVPR.2018.00931"},{"key":"10.1016\/j.patcog.2026.114425_b5","unstructured":"Junhwa Hur, Stefan Roth, Iterative residual refinement for joint optical flow and occlusion estimation, in: IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 5754\u20135763."},{"key":"10.1016\/j.patcog.2026.114425_b6","series-title":"European Conference on Computer Vision","first-page":"402","article-title":"RAFT: Recurrent all-pairs field transforms for optical flow","author":"Teed","year":"2020"},{"key":"10.1016\/j.patcog.2026.114425_b7","series-title":"European Conference on Computer Vision","first-page":"668","article-title":"FlowFormer: A transformer architecture for optical flow","author":"Huang","year":"2022"},{"key":"10.1016\/j.patcog.2026.114425_b8","doi-asserted-by":"crossref","unstructured":"N. Mayer, E. Ilg, P. H\u00e4usser, P. Fischer, D. Cremers, A. Dosovitskiy, T. Brox, A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation, in: IEEE International Conference on CVPR, 2016.","DOI":"10.1109\/CVPR.2016.438"},{"key":"10.1016\/j.patcog.2026.114425_b9","doi-asserted-by":"crossref","unstructured":"D. J. Butler, J. Wulff, G. B. Stanley, M. J. Black, A naturalistic open source movie for optical flow evaluation, in: European Conf. on Computer Vision, ECCV, 2012, pp. 611\u2013625.","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"10.1016\/j.patcog.2026.114425_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.isprsjprs.2017.09.013","article-title":"Object scene flow","author":"Menze","year":"2018","journal-title":"ISPRS J. Photogramm. Remote. Sens. (JPRS)"},{"key":"10.1016\/j.patcog.2026.114425_b11","doi-asserted-by":"crossref","unstructured":"Lukas Mehl, Jenny Schmalfuss, Azin Jahedi, Yaroslava Nalivayko, Andr\u00e9s Bruhn, Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo, in: IEEE Conference on CVPR, 2023.","DOI":"10.1109\/CVPR52729.2023.00482"},{"key":"10.1016\/j.patcog.2026.114425_b12","series-title":"European Conference on Computer Vision","first-page":"288","article-title":"RealFlow: EM-based realistic optical flow dataset generation from videos","author":"Han","year":"2022"},{"key":"10.1016\/j.patcog.2026.114425_b13","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2025.3576851","article-title":"Flow-anything: Learning real-world optical flow estimation from large-scale single-view images","author":"Liang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114425_b14","doi-asserted-by":"crossref","unstructured":"Yang Wang, Yi Yang, Zhenheng Yang, Liang Zhao, Peng Wang, Wei Xu, Occlusion aware unsupervised learning of optical flow, in: IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 4884\u20134893.","DOI":"10.1109\/CVPR.2018.00513"},{"key":"10.1016\/j.patcog.2026.114425_b15","doi-asserted-by":"crossref","unstructured":"Simon Meister, Junhwa Hur, Stefan Roth, UnFlow: Unsupervised learning of optical flow with a bidirectional census loss, in: AAAI Conference on Artificial Intelligence, vol. 32, 2018.","DOI":"10.1609\/aaai.v32i1.12276"},{"key":"10.1016\/j.patcog.2026.114425_b16","doi-asserted-by":"crossref","unstructured":"Hsueh-Ying Lai, Yi-Hsuan Tsai, Wei-Chen Chiu, Bridging stereo matching and optical flow via spatiotemporal correspondence, in: IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 1890\u20131899.","DOI":"10.1109\/CVPR.2019.00199"},{"key":"10.1016\/j.patcog.2026.114425_b17","series-title":"European Conference on Computer Vision","first-page":"557","article-title":"What matters in unsupervised optical flow","author":"Jonschkowski","year":"2020"},{"key":"10.1016\/j.patcog.2026.114425_b18","doi-asserted-by":"crossref","unstructured":"R\u00e9mi Marsal, Florian Chabot, Ang\u00e9lique Loesch, Hichem Sahbi, BrightFlow: Brightness-change-aware unsupervised learning of optical flow, in: IEEE Winter Conference on Applications of Computer Vision, 2023, pp. 2061\u20132070.","DOI":"10.1109\/WACV56688.2023.00210"},{"issue":"2","key":"10.1016\/j.patcog.2026.114425_b19","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1049\/cvi2.12076","article-title":"Improved quadruple sparse census transform and adaptive multi-shape aggregation algorithms for precise stereo matching","volume":"16","author":"Huang","year":"2022","journal-title":"IET Comput. Vis."},{"key":"10.1016\/j.patcog.2026.114425_b20","series-title":"Advances in Visual Computing: 8th International Symposium","first-page":"41","article-title":"Multi-scale integral modified census transform for eye detection","author":"Choi","year":"2012"},{"key":"10.1016\/j.patcog.2026.114425_b21","series-title":"European Conference on Computer Vision","first-page":"151","article-title":"Non-parametric local transforms for computing visual correspondence","author":"Zabih","year":"1994"},{"key":"10.1016\/j.patcog.2026.114425_b22","unstructured":"Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, Saining Xie, A ConvNet for the 2020s, in: IEEE Conference on Computer Vision and Pattern Recognition, 2022, pp. 11976\u201311986."},{"key":"10.1016\/j.patcog.2026.114425_b23","first-page":"1647","article-title":"FlowNet 2.0: Evolution of optical flow estimation with deep networks","author":"Ilg","year":"2017","journal-title":"IEEE Conf. Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114425_b24","doi-asserted-by":"crossref","unstructured":"Anurag Ranjan, Michael J. Black, Optical flow estimation using a spatial pyramid network, in: IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 4161\u20134170.","DOI":"10.1109\/CVPR.2017.291"},{"issue":"6","key":"10.1016\/j.patcog.2026.114425_b25","doi-asserted-by":"crossref","first-page":"1408","DOI":"10.1109\/TPAMI.2019.2894353","article-title":"Models matter, so does training: An empirical study of cnns for optical flow estimation","volume":"42","author":"Sun","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114425_b26","series-title":"2021 IEEE International Conference on Robotics and Automation","first-page":"10310","article-title":"FastFlowNet: A lightweight network for fast optical flow estimation","author":"Kong","year":"2021"},{"key":"10.1016\/j.patcog.2026.114425_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110141","article-title":"Random epipolar constraint loss functions for supervised optical flow estimation","volume":"148","author":"Fan","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114425_b28","series-title":"European Conference on Computer Vision","first-page":"36","article-title":"Sea-RAFT: Simple, efficient, accurate raft for optical flow","author":"Wang","year":"2024"},{"key":"10.1016\/j.patcog.2026.114425_b29","doi-asserted-by":"crossref","unstructured":"Shihao Jiang, Dylan Campbell, Yao Lu, Hongdong Li, Richard Hartley, Learning to estimate hidden motions with global motion aggregation, in: IEEE International Conference on Computer Vision, 2021, pp. 9772\u20139781.","DOI":"10.1109\/ICCV48922.2021.00963"},{"key":"10.1016\/j.patcog.2026.114425_b30","unstructured":"Haofei Xu, Jing Zhang, Jianfei Cai, Hamid Rezatofighi, Dacheng Tao, GMFlow: Learning optical flow via global matching, in: IEEE Conference on Computer Vision and Pattern Recognition, 2022, pp. 8121\u20138130."},{"key":"10.1016\/j.patcog.2026.114425_b31","doi-asserted-by":"crossref","unstructured":"Ao Luo, Xin Li, Fan Yang, Jiangyu Liu, Haoqiang Fan, Shuaicheng Liu, FlowDiffuser: Advancing optical flow estimation with diffusion models, in: IEEE Conference on Computer Vision and Pattern Recognition, 2024, pp. 19167\u201319176.","DOI":"10.1109\/CVPR52733.2024.01813"},{"key":"10.1016\/j.patcog.2026.114425_b32","unstructured":"Yihan Wang, Jia Deng, WAFT: Warping-Alone Field Transforms for Optical Flow, in: The Fourteenth International Conference on Learning Representations, 2026."},{"key":"10.1016\/j.patcog.2026.114425_b33","doi-asserted-by":"crossref","unstructured":"Libo Long, Xiao Hu, Jochen Lang, Shape and Texture: What Influences Reliable Optical Flow Estimation?, in: IEEE Conference on Computer Vision and Pattern Recognition, 2025, pp. 27894\u201327903.","DOI":"10.1109\/CVPR52734.2025.02597"},{"key":"10.1016\/j.patcog.2026.114425_b34","series-title":"Sixth International Conference on Computer Vision","first-page":"839","article-title":"Bilateral filtering for gray and color images","author":"Tomasi","year":"1998"},{"key":"10.1016\/j.patcog.2026.114425_b35","series-title":"European Conference on Computer Vision","first-page":"25","article-title":"High accuracy optical flow estimation based on a theory for warping","author":"Brox","year":"2004"},{"issue":"7","key":"10.1016\/j.patcog.2026.114425_b36","doi-asserted-by":"crossref","first-page":"4282","DOI":"10.1109\/TCSVT.2021.3130281","article-title":"ASFlow: Unsupervised optical flow learning with adaptive pyramid sampling","volume":"32","author":"Liu","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114425_b37","doi-asserted-by":"crossref","unstructured":"Pengpeng Liu, Irwin King, Michael R. Lyu, Jia Xu, DDFlow: Learning optical flow with unlabeled data distillation, in: AAAI Conference on Artificial Intelligence, vol. 33, 2019, pp. 8770\u20138777.","DOI":"10.1609\/aaai.v33i01.33018770"},{"key":"10.1016\/j.patcog.2026.114425_b38","unstructured":"Pengpeng Liu, Michael Lyu, Irwin King, Jia Xu, SelFlow: Self-supervised learning of optical flow, in: IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 4571\u20134580."},{"key":"10.1016\/j.patcog.2026.114425_b39","doi-asserted-by":"crossref","unstructured":"Kunming Luo, Chuan Wang, Shuaicheng Liu, Haoqiang Fan, Jue Wang, Jian Sun, UpFlow: Upsampling pyramid for unsupervised optical flow learning, in: IEEE Conference on Computer Vision and Pattern Recognition, 2021, pp. 1045\u20131054.","DOI":"10.1109\/CVPR46437.2021.00110"},{"key":"10.1016\/j.patcog.2026.114425_b40","doi-asserted-by":"crossref","unstructured":"Shuai Yuan, Lei Luo, Zhuo Hui, Can Pu, Xiaoyu Xiang, Rakesh Ranjan, Denis Demandolx, UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model, in: IEEE Conference on Computer Vision and Pattern Recognition, 2024, pp. 19027\u201319037.","DOI":"10.1109\/CVPR52733.2024.01800"},{"key":"10.1016\/j.patcog.2026.114425_b41","doi-asserted-by":"crossref","unstructured":"Yiran Zhong, Pan Ji, Jianyuan Wang, Yuchao Dai, Hongdong Li, Unsupervised deep epipolar flow for stationary or dynamic scenes, in: IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 12095\u201312104.","DOI":"10.1109\/CVPR.2019.01237"},{"issue":"2","key":"10.1016\/j.patcog.2026.114425_b42","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1109\/TCSVT.2022.3205375","article-title":"MDFlow: Unsupervised optical flow learning by reliable mutual knowledge distillation","volume":"33","author":"Kong","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114425_b43","doi-asserted-by":"crossref","first-page":"6420","DOI":"10.1109\/TIP.2021.3093781","article-title":"OIFlow: Occlusion-inpainting optical flow estimation by unsupervised learning","volume":"30","author":"Liu","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114425_b44","doi-asserted-by":"crossref","unstructured":"Austin Stone, Daniel Maurer, Alper Ayvaci, Anelia Angelova, Rico Jonschkowski, SMURF: Self-teaching multi-frame unsupervised raft with full-image warping, in: IEEE Conference on Computer Vision and Pattern Recognition, 2021, pp. 3887\u20133896.","DOI":"10.1109\/CVPR46437.2021.00388"},{"key":"10.1016\/j.patcog.2026.114425_b45","doi-asserted-by":"crossref","unstructured":"Zhe Ren, Junchi Yan, Bingbing Ni, Bin Liu, Xiaokang Yang, Hongyuan Zha, Unsupervised deep learning for optical flow estimation, in: AAAI Conference on Artificial Intelligence, vol. 31, 2017.","DOI":"10.1609\/aaai.v31i1.10723"},{"key":"10.1016\/j.patcog.2026.114425_b46","article-title":"Stereo matching algorithm for mineral images based on improved BT-census","volume":"216","author":"Lirong","year":"2024","journal-title":"Miner. Eng."},{"key":"10.1016\/j.patcog.2026.114425_b47","doi-asserted-by":"crossref","unstructured":"Liang Liu, Jiangning Zhang, Ruifei He, Yong Liu, Yabiao Wang, Ying Tai, Donghao Luo, Chengjie Wang, Jilin Li, Feiyue Huang, Learning by analogy: Reliable supervision from transformations for unsupervised optical flow estimation, in: IEEE Conference on Computer Vision and Pattern Recognition, 2020, pp. 6489\u20136498.","DOI":"10.1109\/CVPR42600.2020.00652"},{"key":"10.1016\/j.patcog.2026.114425_b48","series-title":"European Conference on Computer Vision","first-page":"363","article-title":"Wavelet convolutions for large receptive fields","author":"Finder","year":"2024"},{"key":"10.1016\/j.patcog.2026.114425_b49","series-title":"European Conference on Computer Vision","first-page":"172","article-title":"Unsupervised learning of optical flow with deep feature similarity","author":"Im","year":"2020"},{"key":"10.1016\/j.patcog.2026.114425_b50","unstructured":"Haipeng Li, Kunming Luo, Shuaicheng Liu, GyroFlow: Gyroscope-guided unsupervised optical flow learning, in: IEEE International Conference on Computer Vision, 2021, pp. 12869\u201312878."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326013907?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326013907?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T12:49:27Z","timestamp":1788526167000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326013907"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":50,"alternative-id":["S0031320326013907"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114425","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Shape-aware unsupervised optical flow via multi-scale recurrent refinement and texture-aware loss","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114425","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114425"}}