{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:59:43Z","timestamp":1782313183946,"version":"3.54.5"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197833","type":"print"},{"value":"9783031197840","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19784-0_24","type":"book-chapter","created":{"date-parts":[[2022,10,30]],"date-time":"2022-10-30T14:02:50Z","timestamp":1667138570000},"page":"409-425","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":74,"title":["Single Stage Virtual Try-On Via\u00a0Deformable Attention Flows"],"prefix":"10.1007","author":[{"given":"Shuai","family":"Bai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiling","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhikang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongxia","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,31]]},"reference":[{"key":"24_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1007\/978-3-030-58565-5_21","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Bertiche","year":"2020","unstructured":"Bertiche, H., Madadi, M., Escalera, S.: CLOTH3D: clothed 3D humans. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 344\u2013359. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_21"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Bhatnagar, B.L., Tiwari, G., Theobalt, C., Pons-Moll, G.: Multi-garment net: Learning to dress 3d people from images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5420\u20135430 (2019)","DOI":"10.1109\/ICCV.2019.00552"},{"key":"24_CR3","unstructured":"Chang, A.X., et al.: Shapenet: an information-rich 3d model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Choi, S., Park, S., Lee, M., Choo, J.: Viton-hd: High-resolution virtual try-on via misalignment-aware normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14131\u201314140 (2021)","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Chopra, A., Jain, R., Hemani, M., Krishnamurthy, B.: Zflow: Gated appearance flow-based virtual try-on with 3d priors. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5433\u20135442 (2021)","DOI":"10.1109\/ICCV48922.2021.00538"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Dong, H., et al.: Towards multi-pose guided virtual try-on network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9026\u20139035 (2019)","DOI":"10.1109\/ICCV.2019.00912"},{"key":"24_CR7","doi-asserted-by":"publisher","unstructured":"Duchon, J.: Splines minimizing rotation-invariant semi-norms in sobolev spaces. In: Constructive Theory of Functions of Several Variables, pp. 85\u2013100. Springer (1977). https:\/\/doi.org\/10.1007\/BFb0086566","DOI":"10.1007\/BFb0086566"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Feng, Y., Wu, F., Shao, X., Wang, Y., Zhou, X.: Joint 3d face reconstruction and dense alignment with position map regression network. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 534\u2013551 (2018)","DOI":"10.1007\/978-3-030-01264-9_33"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Ge, C., Song, Y., Ge, Y., Yang, H., Liu, W., Luo, P.: Disentangled cycle consistency for highly-realistic virtual try-on. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16928\u201316937 (2021)","DOI":"10.1109\/CVPR46437.2021.01665"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Ge, Y., Song, Y., Zhang, R., Ge, C., Liu, W., Luo, P.: Parser-free virtual try-on via distilling appearance flows. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8485\u20138493 (2021)","DOI":"10.1109\/CVPR46437.2021.00838"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Gong, K., Liang, X., Zhang, D., Shen, X., Lin, L.: Look into person: Self-supervised structure-sensitive learning and a new benchmark for human parsing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 932\u2013940 (2017)","DOI":"10.1109\/CVPR.2017.715"},{"key":"24_CR12","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems 27 (2014)"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"G\u00fcler, R.A., Neverova, N., Kokkinos, I.: Densepose: dense human pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7297\u20137306 (2018)","DOI":"10.1109\/CVPR.2018.00762"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Han, X., Hu, X., Huang, W., Scott, M.R.: Clothflow: A flow-based model for clothed person generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10471\u201310480 (2019)","DOI":"10.1109\/ICCV.2019.01057"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Han, X., Wu, Z., Wu, Z., Yu, R., Davis, L.S.: Viton: An image-based virtual try-on network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7543\u20137552 (2018)","DOI":"10.1109\/CVPR.2018.00787"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"24_CR17","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Hore, A., Ziou, D.: Image quality metrics: Psnr vs. ssim. In: 2010 20th International Conference on Pattern Recognition, pp. 2366\u20132369. IEEE (2010)","DOI":"10.1109\/ICPR.2010.579"},{"key":"24_CR19","doi-asserted-by":"publisher","unstructured":"Issenhuth, T., Mary, J., Calauz\u00e8nes, C.: Do not mask what you do not need to mask: a parser-free virtual try-on. In: European Conference on Computer Vision, pp. 619\u2013635. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_37","DOI":"10.1007\/978-3-030-58565-5_37"},{"key":"24_CR20","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: Advances in Neural Information Processing Systems 28 (2015)"},{"key":"24_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"24_CR22","unstructured":"Kitaev, N., Kaiser, \u0141., Levskaya, A.: Reformer: the efficient transformer. arXiv preprint arXiv:2001.04451 (2020)"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Lahner, Z., Cremers, D., Tung, T.: Deepwrinkles: accurate and realistic clothing modeling. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 667\u2013684 (2018)","DOI":"10.1007\/978-3-030-01225-0_41"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Li, K., Chong, M.J., Zhang, J., Liu, J.: Toward accurate and realistic outfits visualization with attention to details. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15546\u201315555 (2021)","DOI":"10.1109\/CVPR46437.2021.01529"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"24_CR26","unstructured":"Liu, P.J., et al.: Generating wikipedia by summarizing long sequences. arXiv preprint arXiv:1801.10198 (2018)"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"24_CR28","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"24_CR29","unstructured":"Minar, M.R., Tuan, T.T., Ahn, H., Rosin, P., Lai, Y.K.: Cp-vton+: clothing shape and texture preserving image-based virtual try-on. In: CVPR Workshops (2020)"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Mir, A., Alldieck, T., Pons-Moll, G.: Learning to transfer texture from clothing images to 3d humans. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7023\u20137034 (2020)","DOI":"10.1109\/CVPR42600.2020.00705"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Qiu, J., Ma, H., Levy, O., Yih, S.W.t., Wang, S., Tang, J.: Blockwise self-attention for long document understanding. arXiv preprint arXiv:1911.02972 (2019)","DOI":"10.18653\/v1\/2020.findings-emnlp.232"},{"key":"24_CR32","unstructured":"Raj, A., Sangkloy, P., Chang, H., Lu, J., Ceylan, D., Hays, J.: Swapnet: garment transfer in single view images. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 666\u2013682 (2018)"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Ren, Y., Wu, Y., Li, T.H., Liu, S., Li, G.: Combining attention with flow for person image synthesis. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3737\u20133745 (2021)","DOI":"10.1145\/3474085.3475256"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Ren, Y., Yu, X., Chen, J., Li, T.H., Li, G.: Deep image spatial transformation for person image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7690\u20137699 (2020)","DOI":"10.1109\/CVPR42600.2020.00771"},{"key":"24_CR35","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training gans. In: Advances in Neural Information Processing Systems 29 (2016)"},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"Seshadrinathan, K., Bovik, A.C.: Unifying analysis of full reference image quality assessment. In: 2008 15th IEEE International Conference on Image Processing, pp. 1200\u20131203. IEEE (2008)","DOI":"10.1109\/ICIP.2008.4711976"},{"key":"24_CR37","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.Y., Kautz, J.: Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8934\u20138943 (2018)","DOI":"10.1109\/CVPR.2018.00931"},{"key":"24_CR39","unstructured":"Tay, Y., Bahri, D., Yang, L., Metzler, D., Juan, D.C.: Sparse sinkhorn attention. In: International Conference on Machine Learning, pp. 9438\u20139447. PMLR (2020)"},{"key":"24_CR40","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"24_CR41","doi-asserted-by":"crossref","unstructured":"Wang, B., Zheng, H., Liang, X., Chen, Y., Lin, L., Yang, M.: Toward characteristic-preserving image-based virtual try-on network. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 589\u2013604 (2018)","DOI":"10.1007\/978-3-030-01261-8_36"},{"key":"24_CR42","unstructured":"Wang, S., Li, B.Z., Khabsa, M., Fang, H., Ma, H.: Linformer: self-attention with linear complexity. arXiv preprint arXiv:2006.04768 (2020)"},{"key":"24_CR43","doi-asserted-by":"crossref","unstructured":"Yang, H., Zhang, R., Guo, X., Liu, W., Zuo, W., Luo, P.: Towards photo-realistic virtual try-on by adaptively generating-preserving image content. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7850\u20137859 (2020)","DOI":"10.1109\/CVPR42600.2020.00787"},{"key":"24_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1007\/978-3-030-59725-2_42","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"H Yu","year":"2020","unstructured":"Yu, H., Chen, X., Shi, H., Chen, T., Huang, T.S., Sun, S.: Motion pyramid networks for accurate and efficient cardiac motion estimation. In: Martel, A.L., Abolmaesumi, P., Stoyanov, D., Mateus, D., Zuluaga, M.A., Zhou, S.K., Racoceanu, D., Joskowicz, L. (eds.) MICCAI 2020. LNCS, vol. 12266, pp. 436\u2013446. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59725-2_42"},{"key":"24_CR45","doi-asserted-by":"crossref","unstructured":"Yu, R., Wang, X., Xie, X.: Vtnfp: an image-based virtual try-on network with body and clothing feature preservation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10511\u201310520 (2019)","DOI":"10.1109\/ICCV.2019.01061"},{"key":"24_CR46","unstructured":"Zablotskaia, P., Siarohin, A., Zhao, B., Sigal, L.: Dwnet: dense warp-based network for pose-guided human video generation. arXiv preprint arXiv:1910.09139 (2019)"},{"key":"24_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1007\/978-3-319-46493-0_18","volume-title":"Computer Vision \u2013 ECCV 2016","author":"T Zhou","year":"2016","unstructured":"Zhou, T., Tulsiani, S., Sun, W., Malik, J., Efros, A.A.: View synthesis by appearance flow. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 286\u2013301. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_18"},{"key":"24_CR48","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19784-0_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:37:03Z","timestamp":1710358623000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19784-0_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197833","9783031197840"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19784-0_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"31 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}