{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:12:33Z","timestamp":1781021553537,"version":"3.54.1"},"reference-count":82,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T00:00:00Z","timestamp":1702857600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T00:00:00Z","timestamp":1702857600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["Project-ID 251654672"],"award-info":[{"award-number":["Project-ID 251654672"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Hierarchical concepts have proven useful in many classical and learning-based optical flow methods regarding both accuracy and robustness. In this paper we show that such concepts are still useful in the context of recent neural networks that follow RAFT\u2019s paradigm refraining from hierarchical strategies by relying on recurrent updates based on a single-scale all-pairs transform. To this end, we introduce MS-RAFT+: a novel recurrent multi-scale architecture based on RAFT that unifies several successful hierarchical concepts. It employs a coarse-to-fine estimation to enable the use of finer resolutions by useful initializations from coarser scales. Moreover, it relies on RAFT\u2019s correlation pyramid that allows to consider non-local cost information during the matching process. Furthermore, it makes use of advanced multi-scale features that incorporate high-level information from coarser scales. And finally, our method is trained subject to a sample-wise robust multi-scale multi-iteration loss that closely supervises each iteration on each scale, while allowing to discard particularly difficult samples. In combination with an appropriate mixed-dataset training strategy, our method performs favorably. It not only yields highly accurate results on the four major benchmarks (KITTI 2015, MPI Sintel, Middlebury and VIPER), it also allows to achieve these results with a single model and a single parameter setting. Our trained model and code are available at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/cv-stuttgart\/MS_RAFT_plus\">https:\/\/github.com\/cv-stuttgart\/MS_RAFT_plus<\/jats:ext-link>.<\/jats:p>","DOI":"10.1007\/s11263-023-01930-7","type":"journal-article","created":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T05:02:11Z","timestamp":1702875731000},"page":"1835-1856","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["MS-RAFT+: High Resolution Multi-Scale RAFT"],"prefix":"10.1007","volume":"132","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3956-0761","authenticated-orcid":false,"given":"Azin","family":"Jahedi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1123-6604","authenticated-orcid":false,"given":"Maximilian","family":"Luz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8005-8365","authenticated-orcid":false,"given":"Marc","family":"Rivinius","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0548-728X","authenticated-orcid":false,"given":"Lukas","family":"Mehl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0423-7411","authenticated-orcid":false,"given":"Andr\u00e9s","family":"Bruhn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,12,18]]},"reference":[{"issue":"1","key":"1930_CR1","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/s11704-015-4246-3","volume":"10","author":"A Ali","year":"2016","unstructured":"Ali, A., Jalil, A., Niu, J., Zhao, X., Rathore, S., Ahmed, J., & Aksam Iftikhar, M. (2016). Visual object tracking\u2013Classical and contemporary approaches. Frontiers of Computer Science, 10(1), 167\u2013188.","journal-title":"Frontiers of Computer Science"},{"issue":"3","key":"1930_CR2","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/BF00158167","volume":"2","author":"P Anandan","year":"1989","unstructured":"Anandan, P. (1989). A computational framework and an algorithm for the measurement of visual motion. International Journal of Computer Vision (IJCV), 2(3), 283\u2013310.","journal-title":"International Journal of Computer Vision (IJCV)"},{"issue":"1","key":"1930_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-010-0390-2","volume":"92","author":"S Baker","year":"2011","unstructured":"Baker, S., Scharstein, D., Lewis, J. P., Roth, S., Black, M. J., & Szeliski, R. (2011). A database and evaluation methodology for optical flow. International Journal of Computer Vision (IJCV), 92(1), 1\u201331.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1930_CR4","doi-asserted-by":"crossref","unstructured":"Barnes, C., Shechtman, E., Finkelstein, A., & Goldman, D. B. (2009). PatchMatch: A randomized correspondence algorithm for structural image editing. ACM Transactions on Graphics (TOG), 28(3), 24:1-24:11.","DOI":"10.1145\/1531326.1531330"},{"key":"1930_CR5","doi-asserted-by":"crossref","unstructured":"Black, M. J., & Anandan, P. (1991). Robust dynamic motion estimation over time. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 296\u2013302).","DOI":"10.1109\/CVPR.1991.139705"},{"key":"1930_CR6","doi-asserted-by":"crossref","unstructured":"Brox, T., Bregler, C., & Malik, J. (2009). Large displacement optical flow. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 41\u201348).","DOI":"10.1109\/CVPR.2009.5206697"},{"key":"1930_CR7","doi-asserted-by":"crossref","unstructured":"Brox, T., Bruhn, A., Papenberg, N., & Weickert, J. (2004). High accuracy optical flow estimation based on a theory for warping. In Proceedomg of the European conference on computer vision (ECCV) (pp. 25\u201336).","DOI":"10.1007\/978-3-540-24673-2_3"},{"key":"1930_CR8","doi-asserted-by":"crossref","unstructured":"Butler, D. J., Wulff, J., Stanley, G. B., & Black, M. J. (2012). A naturalistic open source movie for optical flow evaluation. In Proceeding of the European conference on computer vision (ECCV) (pp. 611\u2013625).","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"1930_CR9","doi-asserted-by":"crossref","unstructured":"Chao, H., Gu, Y., & Napolitano, M. (2013). A survey of optical flow techniques for UAV navigation applications. In Proceeding of the international conference on unmanned aircraft systems (ICUAS) (pp. 710\u2013716).","DOI":"10.1109\/ICUAS.2013.6564752"},{"key":"1930_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Z., Jin, H., Lin, Z., Cohen, S., & Wu, Y. (2013). Large displacement optical flow from nearest neighbor fields. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2013.316"},{"key":"1930_CR11","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Fischer, P., Ilg, E., H\u00e4usser, P., Hazirbas, C., Golkov, V., van der Smagt, P., Cremers, D., & Brox, T. (2015). FlowNet: Learning optical flow with convolutional networks. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) (pp. 2758\u20132766).","DOI":"10.1109\/ICCV.2015.316"},{"key":"1930_CR12","doi-asserted-by":"crossref","unstructured":"Enkelmann, W. (1988). Investigations of multigrid algorithms for the estimation of optical flow fields in image sequences. Computer Vision, Graphics, and Image Processing (CVGIP), 43(2), 150\u2013177.","DOI":"10.1016\/0734-189X(88)90059-X"},{"issue":"1","key":"1930_CR13","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/70.660838","volume":"14","author":"A Giachetti","year":"1998","unstructured":"Giachetti, A., Campani, M., & Torre, V. (1998). The use of optical flow for road navigation. IEEE Transactions on Robotics and Automation (TRA), 14(1), 34\u201348.","journal-title":"IEEE Transactions on Robotics and Automation (TRA)"},{"key":"1930_CR14","doi-asserted-by":"crossref","unstructured":"Han, Y., Luo, K., Luo, A., Liu, J., Fan, H., Luo, G., & Liu, S. (2022). Realflow: EM-based realistic optical flow dataset generation from videos. In Proceedings of the European conference on computer vision (ECCV) (pp. 288\u2013305).","DOI":"10.1007\/978-3-031-19800-7_17"},{"key":"1930_CR15","doi-asserted-by":"crossref","unstructured":"Hofinger, M., Bul\u00f2, S. R., Porzi, L., Knapitsch, A., Pock, T., & Kontschieder, P. (2020). Improving optical flow on a pyramid level. In Proceedings of the European conference on computer vision (ECCV) (pp. 770\u2013786).","DOI":"10.1007\/978-3-030-58604-1_46"},{"key":"1930_CR16","doi-asserted-by":"crossref","unstructured":"Hu, Y., Song, R., & Li, Y. (2016). Efficient coarse-tofine PatchMatch for large displacement optical flow. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5704\u20135712).","DOI":"10.1109\/CVPR.2016.615"},{"key":"1930_CR17","doi-asserted-by":"crossref","unstructured":"Huang, Z., Shi, X., Zhang, C., Wang, Q., Cheung, K. C., Qin, H., Dai, J., & Li, H. (2022). FlowFormer: A transformer architecture for optical flow. In Proceedings of the European conference on computer vision (ECCV) (pp. 668\u2013685).","DOI":"10.1007\/978-3-031-19790-1_40"},{"key":"1930_CR18","volume-title":"Robust statistics","author":"P Huber","year":"2004","unstructured":"Huber, P. (2004). Robust statistics. New York: Wiley."},{"key":"1930_CR19","doi-asserted-by":"crossref","unstructured":"Hui, T.-W., & Loy, C. C. (2020). Lite- FlowNet3: Resolving correspondence ambiguity for more accurate optical flow estimation. In Proceedings of the European conference on computer vision (ECCV) (pp. 169\u2013184).","DOI":"10.1007\/978-3-030-58565-5_11"},{"key":"1930_CR20","doi-asserted-by":"crossref","unstructured":"Hui, T.-W., Tang, X., & Loy, C. C. (2018). Lite- FlowNet: A lightweight convolutional neural network for optical flow estimation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 8981\u20138989).","DOI":"10.1109\/CVPR.2018.00936"},{"issue":"8","key":"1930_CR21","doi-asserted-by":"publisher","first-page":"2555","DOI":"10.1109\/TPAMI.2020.2976928","volume":"43","author":"T-W Hui","year":"2021","unstructured":"Hui, T.-W., Tang, X., & Loy, C. C. (2021). A lightweight optical flow CNN-revisiting data fidelity and regularization. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 43(8), 2555\u20132569.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"1930_CR22","doi-asserted-by":"crossref","unstructured":"Hur, J., & Roth, S. (2019). Iterative residual refinement for joint optical flow and occlusion estimation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 5747\u20135756).","DOI":"10.1109\/CVPR.2019.00590"},{"key":"1930_CR23","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., & Brox, T. (2017). FlowNet 2.0: Evolution of optical flow estimation with deep networks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 1647\u20131655).","DOI":"10.1109\/CVPR.2017.179"},{"key":"1930_CR24","doi-asserted-by":"crossref","unstructured":"Im, W., Lee, S., & Yoon, S. (2022). Semi-supervised learning of optical flow by flow supervisor. In Proceedings of the European conference on computer vision (ECCV) (pp. 302\u2013318). Springer.","DOI":"10.1007\/978-3-031-19833-5_18"},{"key":"1930_CR25","unstructured":"Jaegle, A., Borgeaud, S., Alayrac, J.-B., Doersch, C., Ionescu, C., Ding, D., Koppula, S., Brock, A., Shelhamer, E., H\u2019enaff, O., Botvinick, M. M., Zisserman, A., Vinyals, O., & Carreira, J. (2022). Perceiver IO: A general architecture for structured inputs & outputs. In Proceedings of the international conference on learning representations (ICLR)."},{"key":"1930_CR26","doi-asserted-by":"crossref","unstructured":"Jahedi, A., Mehl, L., Rivinius, M., & Bruhn, A. (2022). Multi-Scale RAFT: Combining hierarchical concepts for learning-based optical flow estimation. IEEE international conference on image processing (ICIP) (pp. 1236\u20131240).","DOI":"10.1109\/ICIP46576.2022.9898048"},{"key":"1930_CR27","doi-asserted-by":"crossref","unstructured":"Janai, J., G\u00fcney, F., Behl, A., & Geiger, A. (2020). Computer vision for autonomous vehicles: Problems, datasets and state of the art (Vol. 12).","DOI":"10.1561\/9781680836899"},{"key":"1930_CR28","doi-asserted-by":"crossref","unstructured":"Janai, J., G\u00fcney, F., Wulff, J., Black, M. J., & Geiger, A. (2017). Slow flow: Exploiting high-speed cameras for accurate and diverse optical flow reference data. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1406\u20131416).","DOI":"10.1109\/CVPR.2017.154"},{"key":"1930_CR29","doi-asserted-by":"crossref","unstructured":"Jeong, J., Lin, J. M., Porikli, F., & Kwak, N. (2022). Imposing consistency for optical flow estimation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 3171\u20133181).","DOI":"10.1109\/CVPR52688.2022.00318"},{"key":"1930_CR30","doi-asserted-by":"crossref","unstructured":"Jiang, S., Campbell, D., Lu, Y., Li, H., & Hartley, R. (2021). Learning to estimate hidden motions with global motion aggregation. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) (pp. 9772\u2013 9781).","DOI":"10.1109\/ICCV48922.2021.00963"},{"key":"1930_CR31","doi-asserted-by":"crossref","unstructured":"Kajo, I., Malik, A. S., & Kamel, N. (2015). Motion estimation of crowd flow using optical flow techniques: A review. In Proceedings of the international conference on signal processing and communication systems (ICSPCS) (pp. 1\u20139).","DOI":"10.1109\/ICSPCS.2015.7391778"},{"key":"1930_CR32","doi-asserted-by":"crossref","unstructured":"Kim, T., Lee, H., & Lee, K. (2013). Optical flow via locally adaptive fusion of complementary data costs. In Proceedings of the IEEE international conference on computer vision (ICCV) (pp. 3344\u20133351).","DOI":"10.1109\/ICCV.2013.415"},{"key":"1930_CR33","doi-asserted-by":"crossref","unstructured":"Kondermann, D., Nair, R., Honauer, K., Krispin, K., Andrulis, J., Brock, A., Gussefeld, B., Rahimimoghaddam, M., Hofmann, S., Brenner, C., & Jahne, B. (2016). The HCI benchmark suite: Stereo and flow ground truth with uncertainties for urban autonomous driving. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops (CVPR-W) (pp. 19\u201328).","DOI":"10.1109\/CVPRW.2016.10"},{"key":"1930_CR34","doi-asserted-by":"crossref","unstructured":"Lai, W.-S., Huang, J.-B., Wang, O., Shechtman, E., Yumer, E., & Yang, M.-H. (2018). Learning blind video temporal consistency. In Proceedings of the European conference on computer vision (ECCV) (pp. 179\u2013195).","DOI":"10.1007\/978-3-030-01267-0_11"},{"key":"1930_CR35","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, P., Xiong, P., Cai, T., Yan, Z., Yang, L., Liu, J., Fan, H., & Liu, S. (2022). Practical stereo matching via cascaded recurrent network with adaptive correlation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 16263\u201316272).","DOI":"10.1109\/CVPR52688.2022.01578"},{"key":"1930_CR36","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature Pyramid Networks for Object Detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 936\u2013944).","DOI":"10.1109\/CVPR.2017.106"},{"key":"1930_CR37","doi-asserted-by":"crossref","unstructured":"Liu, H., Lu, T., Xu, Y., Liu, J., Li, W., & Chen, L. (2022). CamLiFlow: Bidirectional camera-LiDAR fusion for joint optical flow and scene flow estimation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 5791\u20135801).","DOI":"10.1109\/CVPR52688.2022.00570"},{"key":"1930_CR38","doi-asserted-by":"crossref","unstructured":"Long, L., & Lang, J. (2022). Detail preserving residual feature pyramid modules for optical flow. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision (WACV) (pp. 2100\u20132108).","DOI":"10.1109\/WACV51458.2022.00403"},{"key":"1930_CR39","doi-asserted-by":"crossref","unstructured":"Lu, Y., Valmadre, J., Wang, H., Kannala, J., Harandi, M., & Torr, P. H. S. (2020). Devon: Deformable volume network for learning optical flow. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision (WACV) (pp. 2694\u20132702).","DOI":"10.1109\/WACV45572.2020.9093590"},{"key":"1930_CR40","unstructured":"Lucas, B. D., & Kanade, T. (1981). An iterative image registration technique with an application to stereo vision. In Proceedings of the international joint conference on artificial intelligence (IJCAI) (pp. 674\u2013679)."},{"key":"1930_CR41","doi-asserted-by":"crossref","unstructured":"Luo, A., Yang, F., Li, X., & Liu, S. (2022). Learning optical flow with kernel patch attention. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 8896\u20138905).","DOI":"10.1109\/CVPR52688.2022.00870"},{"key":"1930_CR42","doi-asserted-by":"crossref","unstructured":"Luo, A., Yang, F., Luo, K., Li, X., Fan, H., & Liu, S. (2022). Learning optical flow with adaptive graph reasoning. In Proceedings of the AAAI conference on artificial intelligence (AAAI).","DOI":"10.1609\/aaai.v36i2.20083"},{"key":"1930_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2020.103448","volume":"293","author":"W Luo","year":"2021","unstructured":"Luo, W., Xing, J., Milan, A., Zhang, X., Liu, W., & Kim, T.-K. (2021). Multiple object tracking: A literature review. Artificial Intelligence (AI), 293, 103448.","journal-title":"Artificial Intelligence (AI)"},{"key":"1930_CR44","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.neucom.2017.12.040","volume":"283","author":"Z Mahfouf","year":"2018","unstructured":"Mahfouf, Z., Merouani, H. F., Bouchrika, I., & Harrati, N. (2018). Investigating the use of motion-based features from optical flow for gait recognition. Neurocomputing (NC), 283, 140\u2013149.","journal-title":"Neurocomputing (NC)"},{"key":"1930_CR45","doi-asserted-by":"crossref","unstructured":"Mayer, N., Ilg, E., Hausser, P., Fischer, P., Cremers, D., Dosovitskiy, A., & Brox, T. (2016). A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 4040-4048).","DOI":"10.1109\/CVPR.2016.438"},{"key":"1930_CR46","doi-asserted-by":"crossref","unstructured":"Menze, M., & Geiger, A. (2015). Object scene flow for autonomous vehicles. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 3061\u20133070).","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"1930_CR47","doi-asserted-by":"crossref","unstructured":"Philipp, M., Bacher, N., Saur, S., Mathis-Ullrich, F., & Bruhn, A. (2022). From chairs to brains: Customizing optical flow for surgical activity localization. In IEEE international symposium on biomedical imaging (ISBI): Proceedings","DOI":"10.1109\/ISBI52829.2022.9761704"},{"key":"1930_CR48","doi-asserted-by":"crossref","unstructured":"Ranjan, A., & Black, M. J. (2017). Optical flow estimation using a spatial pyramid network. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 2720\u20132729).","DOI":"10.1109\/CVPR.2017.291"},{"issue":"4","key":"1930_CR49","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1007\/s11263-019-01279-w","volume":"128","author":"A Ranjan","year":"2020","unstructured":"Ranjan, A., Hoffmann, D. T., Tzionas, D., Tang, S., Romero, J., & Black, M. J. (2020). Learning multi-human optical flow. International Journal of Computer Vision (IJCV), 128(4), 873\u2013890.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1930_CR50","doi-asserted-by":"crossref","unstructured":"Richter, S. R., Hayder, Z., & Koltun, V. (2017). Playing for benchmarks. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) (pp. 2232\u20132241).","DOI":"10.1109\/ICCV.2017.243"},{"key":"1930_CR51","doi-asserted-by":"crossref","unstructured":"Rishav, Schuster, R., Battrawy, R., Wasenm\u00fcller, O., & Stricker, D. (2021). ResFPN: Residual skip connections in multi-resolution feature pyramid networks for accurate dense pixel matching. In Proceedings of the international conference on pattern recognition (ICPR) (pp. 180\u2013187).","DOI":"10.1109\/ICPR48806.2021.9412750"},{"key":"1930_CR52","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In Proceedings of the international conference on medical image computing and computer-assisted intervention (MICCAI) (pp. 234\u2013241).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1930_CR53","doi-asserted-by":"crossref","unstructured":"Saxena, R., Schuster, R., Wasenmuller, O., & Stricker, D. (2019). PWOC-3D: Deep occlusion-aware end-to-end scene flow estimation. In Proceedings of the IEEE intelligent vehicles symposium (IV) (pp. 324\u2013331).","DOI":"10.1109\/IVS.2019.8814146"},{"key":"1930_CR54","doi-asserted-by":"crossref","unstructured":"Sevilla-Lara, L., Liao, Y., G\u00fcney, F., Jampani, V., Geiger, A., & Black, M. J. (2019). On the integration of optical flow and action recognition. In Proceedings of the german conference on pattern recognition (GCPR) (pp. 281\u2013297).","DOI":"10.1007\/978-3-030-12939-2_20"},{"key":"1930_CR55","unstructured":"Shrivastava, A., Sukthankar, R., Malik, J., & Gupta, A. (2017). Beyond skip connections: Topdown modulation for object detection arXiv:1612.06851"},{"issue":"1","key":"1930_CR56","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11831-019-09375-3","volume":"28","author":"JP Singh","year":"2021","unstructured":"Singh, J. P., Jain, S., Arora, S., & Singh, U. P. (2021). A survey of behavioral biometric gait recognition: Current success and future perspectives. Archives of Computational Methods in Engineering (ACME), 28(1), 107\u2013148.","journal-title":"Archives of Computational Methods in Engineering (ACME)"},{"issue":"1","key":"1930_CR57","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1186\/s40537-019-0212-5","volume":"6","author":"G Sreenu","year":"2019","unstructured":"Sreenu, G., & Saleem Durai, M. A. (2019). Intelligent video surveillance: A review through deep learning techniques for crowd analysis. Journal of Big Data, 6(1), 48.","journal-title":"Journal of Big Data"},{"key":"1930_CR58","doi-asserted-by":"crossref","unstructured":"Sui, X., Li, S., Geng, X., Wu, Y., Xu, X., Liu, Y., Goh, R. & Zhu, H. (2022). CRAFT: Crossattentional flow transformer for robust optical flow. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 17581\u201317590).","DOI":"10.1109\/CVPR52688.2022.01708"},{"key":"1930_CR59","doi-asserted-by":"crossref","unstructured":"Sun, D., Herrmann, C., Reda, F. A., Rubinstein, M., Fleet, D. J., & Freeman, W. T. (2022). Disentangling architecture and training for optical flow. In Proceedings of the European conference on computer vision (ECCV) (pp. 165\u2013182).","DOI":"10.1007\/978-3-031-20047-2_10"},{"key":"1930_CR60","doi-asserted-by":"crossref","unstructured":"Sun, D., Vlasic, D., Herrmann, C., Jampani, V., Krainin, M., Chang, H., Zabih, R., Freeman, W. T. & Liu, C. (2021). AutoFlow: learning a better training set for optical flow. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 10093\u201310102).","DOI":"10.1109\/CVPR46437.2021.00996"},{"key":"1930_CR61","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.-Y., & Kautz, J. (2018). PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 8934\u20138943).","DOI":"10.1109\/CVPR.2018.00931"},{"issue":"6","key":"1930_CR62","doi-asserted-by":"publisher","first-page":"1408","DOI":"10.1109\/TPAMI.2019.2894353","volume":"42","author":"D Sun","year":"2020","unstructured":"Sun, D., Yang, X., Liu, M.-Y., & Kautz, J. (2020). Models matter, so does training: An empirical study of CNNs for optical flow estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 42(6), 1408\u20131423.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"1930_CR63","unstructured":"Sun, S., Chen, Y., Zhu, Y., Gou, G., & Li, G. (2022). Learning optical flow with super kernels. In Proceedings of the conference on neural information processing systems (NeurIPS)."},{"key":"1930_CR64","doi-asserted-by":"crossref","unstructured":"Teed, Z., & Deng, J. (2020). RAFT: Recurrent allpairs field transforms for optical flow. In Proceedings of the European conference on computer vision (ECCV) (pp. 402\u2013419).","DOI":"10.1007\/978-3-030-58536-5_24"},{"issue":"8","key":"1930_CR65","doi-asserted-by":"publisher","first-page":"6505","DOI":"10.1007\/s10462-022-10159-8","volume":"55","author":"Z Tu","year":"2022","unstructured":"Tu, Z., Li, H., Xie, W., Liu, Y., Zhang, S., Li, B., & Yuan, J. (2022). Optical flow for video super-resolution: A survey. Artificial Intelligence Review, 55(8), 6505\u20136546.","journal-title":"Artificial Intelligence Review"},{"key":"1930_CR66","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1016\/j.patcog.2015.09.002","volume":"50","author":"Z Tu","year":"2016","unstructured":"Tu, Z., Poppe, R., & Veltkamp, R. C. (2016). Weighted local intensity fusion method for variational optical flow estimation. Pattern Recognition (PR), 50, 223\u2013232.","journal-title":"Pattern Recognition (PR)"},{"key":"1930_CR67","doi-asserted-by":"crossref","unstructured":"Volz, S., Bruhn, A., Valgaerts, L., & Zimmer, H. (2011). Modeling temporal coherence for optical flow. In Proceedings of the IEEE international conference on computer vision (ICCV) (pp. 1116\u20131123).","DOI":"10.1109\/ICCV.2011.6126359"},{"key":"1930_CR68","unstructured":"Wan, Z., Mao, Y., & Dai, Y. (2020). PRAFlow RVC: Pyramid recurrent all-pairs field transforms for optical flow estimation in Robust Vision Challenge 2020. arXiv:2009.06360 [cs]."},{"key":"1930_CR69","doi-asserted-by":"crossref","unstructured":"Wang, H., Fan, R., & Liu, M. (2020). CoTAMFlow: Adaptive modulation network with co-teaching strategy for unsupervised optical flow estimation. In Proceedings of the conference on robot learning (CoRL) (pp. 143\u2013155).","DOI":"10.36227\/techrxiv.13186688"},{"key":"1930_CR70","doi-asserted-by":"crossref","unstructured":"Xu, H., Yang, J., Cai, J., Zhang, J., & Tong, X. (2021). High-resolution optical flow from 1D attention and correlation. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) (pp. 10498\u2013 10507).","DOI":"10.1109\/ICCV48922.2021.01033"},{"key":"1930_CR71","doi-asserted-by":"crossref","unstructured":"Xu, H., Zhang, J., Cai, J., Rezatofighi, H., & Tao, D. (2022). GMFlow: Learning optical flow via global matching. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 8111\u20138120).","DOI":"10.1109\/CVPR52688.2022.00795"},{"issue":"9","key":"1930_CR72","doi-asserted-by":"crossref","first-page":"1744","DOI":"10.1109\/TPAMI.2011.236","volume":"34","author":"L Xu","year":"2011","unstructured":"Xu, L., Jia, J., & Matsushita, Y. (2011). Motion detail preserving optical flow estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 34(9), 1744\u20131757.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"1930_CR73","unstructured":"Yang, G., & Ramanan, D. (2019). Volumetric correspondence networks for optical flow. In Proceedings of conference on neural information processing systems (NeuRIPS)."},{"key":"1930_CR74","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.patrec.2018.05.018","volume":"118","author":"G Yao","year":"2019","unstructured":"Yao, G., Lei, T., & Zhong, J. (2019). A review of convolutional-neural-network-based action recognition. Pattern Recognition Letters (PRL), 118, 14\u201322.","journal-title":"Pattern Recognition Letters (PRL)"},{"key":"1930_CR75","doi-asserted-by":"crossref","unstructured":"Yin, Z., Darrell, T., & Yu, F. (2019). Hierarchical discrete distribution decomposition for match density estimation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 6037\u20136046).","DOI":"10.1109\/CVPR.2019.00620"},{"issue":"4","key":"1930_CR76","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/s40903-015-0032-7","volume":"1","author":"K Yousif","year":"2015","unstructured":"Yousif, K., Bab-Hadiashar, A., & Hoseinnezhad, R. (2015). An overview to visual odometry and visual SLAM: Applications to mobile robotics. Intelligent Industrial Systems, 1(4), 289\u2013311.","journal-title":"Intelligent Industrial Systems"},{"key":"1930_CR77","unstructured":"Zendel, O., Dai, A., Fernandez, X. P., Geiger, A., Koltun, V., Kontschieder, P., ... Wulff, J. (2022). ECCV 2022 robust vision challenge. (http:\/\/www.robustvision.net\/)"},{"key":"1930_CR78","doi-asserted-by":"crossref","unstructured":"Zhang, F., Woodford, O. J., Prisacariu, V. A., & Torr, P. H. S. (2021). Separable Flow: Learning motion cost volumes for optical flow estimation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 10807\u201310817).","DOI":"10.1109\/ICCV48922.2021.01063"},{"key":"1930_CR79","doi-asserted-by":"publisher","first-page":"13291","DOI":"10.1007\/s11042-020-08633-y","volume":"79","author":"F Zhang","year":"2020","unstructured":"Zhang, F., Xu, S., & Zhang, X. (2020). High accuracy correspondence field estimation via MST based patch matching. Multimedia Tools and Applications, 79, 13291\u201313309.","journal-title":"Multimedia Tools and Applications"},{"key":"1930_CR80","doi-asserted-by":"crossref","unstructured":"Zhao, S., Sheng, Y., Dong, Y., Chang, E., & Xu, Y. (2020). MaskFlownet: Asymmetric feature matching with learnable occlusion mask. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 6278\u20136287).","DOI":"10.1109\/CVPR42600.2020.00631"},{"key":"1930_CR81","doi-asserted-by":"crossref","unstructured":"Zhao, S., Zhao, L., Zhang, Z., Zhou, E., & Metaxas, D. N. (2022). Global matching with overlapping attention for optical flow estimation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 17571\u201317580).","DOI":"10.1109\/CVPR52688.2022.01707"},{"key":"1930_CR82","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Nie, N., Ling, Z., Xiong, P., Liu, J., Wang, H., & Li, J. (2022). DIP: Deep inverse patchmatch for high-resolution optical flow. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 8925\u20138934).","DOI":"10.1109\/CVPR52688.2022.00872"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01930-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01930-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01930-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T08:20:19Z","timestamp":1715070019000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01930-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,18]]},"references-count":82,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["1930"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01930-7","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,18]]},"assertion":[{"value":"16 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 December 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}