{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T13:04:06Z","timestamp":1760101446021,"version":"3.37.3"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T00:00:00Z","timestamp":1687564800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T00:00:00Z","timestamp":1687564800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1007\/s11263-023-01828-4","type":"journal-article","created":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T15:03:47Z","timestamp":1687619027000},"page":"2757-2769","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["RAFT-MSF: Self-Supervised Monocular Scene Flow Using Recurrent Optimizer"],"prefix":"10.1007","volume":"131","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1553-932X","authenticated-orcid":false,"given":"Bayram","family":"Bayramli","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhwa","family":"Hur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongtao","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,24]]},"reference":[{"key":"1828_CR1","doi-asserted-by":"crossref","unstructured":"Basha, T., Moses, Y., & Kiryati, N. (2010). Multi-view scene flow estimation: A view centered variational approach. In CVPR.","DOI":"10.1109\/CVPR.2010.5539791"},{"key":"1828_CR2","doi-asserted-by":"crossref","unstructured":"Brickwedde, F., Abraham, S., & Mester, R. (2019). Mono-SF: Multi-view geometry meets single-view depth for monocular scene flow estimation of dynamic traffic scenes. In ICCV, pp. 2780\u20132790.","DOI":"10.1109\/ICCV.2019.00287"},{"key":"1828_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., Schmid, C., & Sminchisescu, C. (2019). Self-supervised learning with geometric constraints in monocular video: Connecting flow, depth, and camera. In ICCV, pp. 7062\u20137071.","DOI":"10.1109\/ICCV.2019.00716"},{"key":"1828_CR4","unstructured":"Eigen, D., Puhrsch, C., & Fergus, R. (2014). Depth map prediction from a single image using a multi-scale deep network. In NIPS."},{"key":"1828_CR5","first-page":"1231","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013). Vision meets robotics: The KITTI dataset. IJRR, 32, 1231\u20131237.","journal-title":"IJRR"},{"key":"1828_CR6","doi-asserted-by":"crossref","unstructured":"Godard, C., Aodha, O.\u00a0M., & Brostow, G.\u00a0J. (2017). Unsupervised monocular depth estimation with left-right consistency. In CVPR, pp. 6602\u20136611.","DOI":"10.1109\/CVPR.2017.699"},{"key":"1828_CR7","doi-asserted-by":"crossref","unstructured":"Godard, C., Aodha, O.\u00a0M., & Brostow, G.\u00a0J. (2019). Digging into self-supervised monocular depth estimation. In ICCV, pp. 3827\u20133837.","DOI":"10.1109\/ICCV.2019.00393"},{"key":"1828_CR8","doi-asserted-by":"crossref","unstructured":"Gu, X., Wang, Y., Wu, C., Lee, Y.\u00a0J., \u00a0 & Wang, P. (2019). HPLFlowNet: Hierarchical permutohedral lattice flownet for scene flow estimation on large-scale point clouds. In CVPR, pp. 3249\u20133258 .","DOI":"10.1109\/CVPR.2019.00337"},{"key":"1828_CR9","doi-asserted-by":"crossref","unstructured":"Hur, J., & Roth, S. (2020). Self-supervised monocular scene flow estimation. In CVPR, pp. 7394\u20137403.","DOI":"10.1109\/CVPR42600.2020.00742"},{"key":"1828_CR10","doi-asserted-by":"crossref","unstructured":"Hur, J., & Roth, S. (2021). Self-supervised multi-frame monocular scene flow. In CVPR, pp. 2683\u20132693.","DOI":"10.1109\/CVPR46437.2021.00271"},{"key":"1828_CR11","unstructured":"Kingma, D.\u00a0P., & Ba, J. (2015). Adam: A method for stochastic optimization. In ICLR."},{"key":"1828_CR12","doi-asserted-by":"crossref","unstructured":"Liu, L., Zhai, G., Ye, W., & Liu, Y. (2019a). Unsupervised learning of scene flow estimation fusing with local rigidity. In IJCAI.","DOI":"10.24963\/ijcai.2019\/123"},{"key":"1828_CR13","doi-asserted-by":"crossref","unstructured":"Liu, X., Qi, C., & Guibas, L.\u00a0J. (2019b). FlowNet3D: Learning scene flow in 3d point clouds. CVPR, pp. 529\u2013537.","DOI":"10.1109\/CVPR.2019.00062"},{"key":"1828_CR14","doi-asserted-by":"publisher","first-page":"2624","DOI":"10.1109\/TPAMI.2019.2930258","volume":"42","author":"C Luo","year":"2020","unstructured":"Luo, C., Yang, Z., Wang, P., Wang, Y., Xu, W., Nevatia, R., & Yuille, A. (2020). Every pixel counts++: Joint learning of geometry and motion with 3D holistic understanding. IEEE TPAMI, 42, 2624\u20132641.","journal-title":"IEEE TPAMI"},{"key":"1828_CR15","doi-asserted-by":"crossref","unstructured":"Meister, S., Hur, J., & Roth, S. (2018). Unflow: Unsupervised learning of optical flow with a bidirectional census loss. In AAAI.","DOI":"10.1609\/aaai.v32i1.12276"},{"key":"1828_CR16","doi-asserted-by":"crossref","unstructured":"Peng, R., Wang, R., Lai, Y., Tang, L., & Cai, Y. (2021). Excavating the potential capacity of self-supervised monocular depth estimation. In ICCV.","DOI":"10.1109\/ICCV48922.2021.01527"},{"key":"1828_CR17","unstructured":"Qi, C., Yi, L., Su, H., & Guibas, L.\u00a0J. (2017). Pointnet++: Deep hierarchical feature learning on point sets in a metric space. In NIPS."},{"key":"1828_CR18","doi-asserted-by":"crossref","unstructured":"Ramamonjisoa, M., Firman, M., Watson, J., Lepetit, V., & Turmukhambetov, D. (2021). Single image depth prediction with wavelet decomposition. In CVPR, pp. 11084\u201311093.","DOI":"10.1109\/CVPR46437.2021.01094"},{"key":"1828_CR19","doi-asserted-by":"crossref","unstructured":"Ranjan, A., Jampani, V., Balles, L., Kim, K., Sun, D., Wulff, J., Black, M.\u00a0J. (2019). Competitive collaboration: Joint unsupervised learning of depth, camera motion, optical flow and motion segmentation. In CVPR, pp. 12232\u201312241.","DOI":"10.1109\/CVPR.2019.01252"},{"key":"1828_CR20","doi-asserted-by":"crossref","unstructured":"Schuster, R., Unger, C., & Stricker, D. (2020). MonoComb: A sparse-to-dense combination approach for monocular scene flow. In Computer Science in Cars Symposium.","DOI":"10.1145\/3385958.3430473"},{"key":"1828_CR21","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 CVPR, pp. 8934\u20138943.","DOI":"10.1109\/CVPR.2018.00931"},{"key":"1828_CR22","doi-asserted-by":"crossref","unstructured":"Teed, Z., & Deng, J. (2020). RAFT: Recurrent all-pairs field transforms for optical flow. In ECCV.","DOI":"10.24963\/ijcai.2021\/662"},{"key":"1828_CR23","doi-asserted-by":"crossref","unstructured":"Teed, Z., & Deng, J. (2021). RAFT-3D: Scene flow using rigid-motion embeddings. In CVPR, pp. 8371\u20138380.","DOI":"10.1109\/CVPR46437.2021.00827"},{"key":"1828_CR24","doi-asserted-by":"crossref","unstructured":"Valgaerts, L., Bruhn, A., Zimmer, H., Weickert, J., Stoll, C., & Theobalt, C. (2010). Joint estimation of motion, structure and geometry from stereo sequences. In ECCV.","DOI":"10.1007\/978-3-642-15561-1_41"},{"key":"1828_CR25","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1109\/TPAMI.2005.63","volume":"27","author":"S Vedula","year":"2005","unstructured":"Vedula, S., Baker, S., Rander, P., Collins, R. T., & Kanade, T. (2005). Three-dimensional scene flow. EEE TPAMI, 27, 475\u2013480.","journal-title":"EEE TPAMI"},{"key":"1828_CR26","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing, 13, 600\u2013612.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1828_CR27","doi-asserted-by":"crossref","unstructured":"Wang, Z., Li, S., Howard-Jenkins, H., Prisacariu, V.\u00a0A., & Chen, M. (2020). FlowNet3D++: Geometric losses for deep scene flow estimation. In WACV, pp. 91\u201398.","DOI":"10.1109\/WACV45572.2020.9093302"},{"key":"1828_CR28","doi-asserted-by":"crossref","unstructured":"Watson, J., Firman, M., Brostow, G.\u00a0J., & Turmukhambetov, D. (2019). Self-supervised monocular depth hints. In ICCV, pp. 2162\u20132171.","DOI":"10.1109\/ICCV.2019.00225"},{"key":"1828_CR29","doi-asserted-by":"crossref","unstructured":"Wu, W., Wang, Z., Li, Z., Liu, W., & Li, F. (2020). Pointpwc-net: Cost volume on point clouds for (self-)supervised scene flow estimation. In ECCV.","DOI":"10.1007\/978-3-030-58558-7_6"},{"key":"1828_CR30","doi-asserted-by":"crossref","unstructured":"Yang, G., & Ramanan, D. (2020). Upgrading optical flow to 3D scene flow through optical expansion. In CVPR, pp. 1331\u20131340.","DOI":"10.1109\/CVPR42600.2020.00141"},{"key":"1828_CR31","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, P., Wang, Y., Xu, W., & Nevatia, R. (2018). Every pixel counts: Unsupervised geometry learning with holistic 3D motion understanding. In ECCV Workshops.","DOI":"10.1007\/978-3-030-11021-5_43"},{"key":"1828_CR32","doi-asserted-by":"crossref","unstructured":"Yin, Z., & Shi, J. (2018). GeoNet: Unsupervised learning of dense depth, optical flow and camera pose. In CVPR, pp. 1983\u20131992.","DOI":"10.1109\/CVPR.2018.00212"},{"key":"1828_CR33","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Fan, X., Shi, P., & Xin, Y. (2021). R-MSFM: Recurrent multi-scale feature modulation for monocular depth estimating. In ICCV, pp. 12777\u201312786.","DOI":"10.1109\/ICCV48922.2021.01254"},{"key":"1828_CR34","doi-asserted-by":"crossref","unstructured":"Zou, Y., Luo, Z., & Huang, J.-B. (2018). DF-Net: Unsupervised joint learning of depth and flow using cross-task consistency. In ECCV.","DOI":"10.1007\/978-3-030-01228-1_3"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01828-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01828-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01828-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T04:03:57Z","timestamp":1695614637000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01828-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,24]]},"references-count":34,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["1828"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01828-4","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2023,6,24]]},"assertion":[{"value":"29 May 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}