{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T14:10:29Z","timestamp":1758723029577,"version":"3.44.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T00:00:00Z","timestamp":1751155200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T00:00:00Z","timestamp":1751155200000},"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":["Vis Comput"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s00371-025-04075-5","type":"journal-article","created":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T22:29:37Z","timestamp":1751149777000},"page":"10883-10895","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AFDiT: flow-guided transformer diffusion for structure-aware virtual try-on"],"prefix":"10.1007","volume":"41","author":[{"given":"Huiming","family":"Ding","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beining","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengtian","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhifeng","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,29]]},"reference":[{"key":"4075_CR1","doi-asserted-by":"publisher","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\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7543\u20137552 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00787","DOI":"10.1109\/CVPR.2018.00787"},{"key":"4075_CR2","doi-asserted-by":"publisher","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). Lecture Notes in Computer Science, vol. 11217, pp. 607\u2013623 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_36","DOI":"10.1007\/978-3-030-01261-8_36"},{"key":"4075_CR3","doi-asserted-by":"publisher","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 (CVPR), pp. 14131\u201314140 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01391","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"4075_CR4","doi-asserted-by":"publisher","unstructured":"Lee, S., Gu, G., Park, S., Choi, S., Choo, J.: High-resolution virtual try-on with misalignment and occlusion-handled conditions. In: Proceedings of the European Conference on Computer Vision (ECCV). Lecture Notes in Computer Science, vol. 13677, pp. 204\u2013219 (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_13","DOI":"10.1007\/978-3-031-19790-1_13"},{"key":"4075_CR5","doi-asserted-by":"publisher","first-page":"6595","DOI":"10.1109\/TMM.2024.3354622","volume":"26","author":"N Fang","year":"2024","unstructured":"Fang, N., Qiu, L., Zhang, S., Wang, Z., Hu, K.: Pg-vton: A novel image-based virtual try-on method via progressive inference paradigm. IEEE Trans. Multimed. 26, 6595\u20136608 (2024). https:\/\/doi.org\/10.1109\/TMM.2024.3354622","journal-title":"IEEE Trans. Multimed."},{"key":"4075_CR6","doi-asserted-by":"publisher","unstructured":"Han, X., Huang, W., Hu, X., Scott, M.R.: Clothflow: A flow-based model for clothed person generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10470\u201310479 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.01057","DOI":"10.1109\/ICCV.2019.01057"},{"key":"4075_CR7","doi-asserted-by":"publisher","unstructured":"Yang, H., Zhang, R., Guo, X., Liu, W., Zuo, W., Luo, P.: Towards photo-realistic virtual try-on by adaptively generating$$\\leftrightarrow $$preserving image content. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7847\u20137856 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00787","DOI":"10.1109\/CVPR42600.2020.00787"},{"key":"4075_CR8","doi-asserted-by":"publisher","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 (CVPR), pp. 8485\u20138493 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00838","DOI":"10.1109\/CVPR46437.2021.00838"},{"key":"4075_CR9","doi-asserted-by":"publisher","unstructured":"He, S., Song, Y., Xiang, T.: Style-based global appearance flow for virtual try-on. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3460\u20133469 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00346","DOI":"10.1109\/CVPR52688.2022.00346"},{"key":"4075_CR10","doi-asserted-by":"publisher","unstructured":"Bai, S., Zhou, H., Li, Z., Zhou, C., Yang, H.: Single stage virtual try-on via deformable attention flows. In: Proceedings of the European Conference on Computer Vision (ECCV). Lecture Notes in Computer Science, vol. 13675, pp. 409\u2013425 (2022). https:\/\/doi.org\/10.1007\/978-3-031-19784-0_24","DOI":"10.1007\/978-3-031-19784-0_24"},{"key":"4075_CR11","doi-asserted-by":"publisher","unstructured":"Kim, J., Gu, G., Park, M., Park, S., Choo, J.: Stableviton: Learning semantic correspondence with latent diffusion model for virtual try-on. CoRR abs\/2312.01725 (2023) https:\/\/doi.org\/10.48550\/ARXIV.2312.01725","DOI":"10.48550\/ARXIV.2312.01725"},{"key":"4075_CR12","doi-asserted-by":"publisher","unstructured":"Morelli, D., Baldrati, A., Cartella, G., Cornia, M., Bertini, M., Cucchiara, R.: Ladi-vton: Latent diffusion textual-inversion enhanced virtual try-on. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 8580\u20138589 (2023). https:\/\/doi.org\/10.1145\/3581783.3612137","DOI":"10.1145\/3581783.3612137"},{"issue":"7","key":"4075_CR13","doi-asserted-by":"publisher","first-page":"2583","DOI":"10.1007\/S00371-022-02480-8","volume":"39","author":"Y Chang","year":"2023","unstructured":"Chang, Y., Peng, T., Yu, F., He, R., Hu, X., Liu, J., Zhang, Z., Jiang, M.: VTNCT: an image-based virtual try-on network by combining feature with pixel transformation. Vis. Comput. 39(7), 2583\u20132596 (2023). https:\/\/doi.org\/10.1007\/S00371-022-02480-8","journal-title":"Vis. Comput."},{"key":"4075_CR14","doi-asserted-by":"publisher","unstructured":"Xu, Y., Gu, T., Chen, W., Chen, A.: Ootdiffusion: Outfitting fusion based latent diffusion for controllable virtual try-on. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 8996\u20139004 (2025). https:\/\/doi.org\/10.1609\/AAAI.V39I9.32973","DOI":"10.1609\/AAAI.V39I9.32973"},{"key":"4075_CR15","doi-asserted-by":"publisher","unstructured":"Choi, Y., Kwak, S., Lee, K., Choi, H., Shin, J.: Improving diffusion models for authentic virtual try-on in the wild. In: Proceedings of the European Conference on Computer Vision (ECCV). Lecture Notes in Computer Science, vol. 15144, pp. 206\u2013235 (2024). https:\/\/doi.org\/10.1007\/978-3-031-73016-0_13","DOI":"10.1007\/978-3-031-73016-0_13"},{"key":"4075_CR16","doi-asserted-by":"publisher","unstructured":"Jiang, B., Hu, X., Luo, D., He, Q., Xu, C., Peng, J., Zhang, J., Wang, C., Wu, Y., Fu, Y.: Fitdit: Advancing the authentic garment details for high-fidelity virtual try-on. CoRR abs\/2411.10499 (2024) https:\/\/doi.org\/10.48550\/ARXIV.2411.10499","DOI":"10.48550\/ARXIV.2411.10499"},{"issue":"5","key":"4075_CR17","doi-asserted-by":"publisher","first-page":"3297","DOI":"10.1007\/S00371-024-03603-Z","volume":"41","author":"J Ye","year":"2025","unstructured":"Ye, J., Wang, Y., Xie, F., Wang, Q., Gu, X., Wu, Z.: Slot-vton: subject-driven diffusion-based virtual try-on with slot attention. Vis. Comput. 41(5), 3297\u20133308 (2025). https:\/\/doi.org\/10.1007\/S00371-024-03603-Z","journal-title":"Vis. Comput."},{"key":"4075_CR18","doi-asserted-by":"publisher","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10674\u201310685 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01042","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"4075_CR19","unstructured":"Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., M\u00fcller, J., Penna, J., Rombach, R.: SDXL: improving latent diffusion models for high-resolution image synthesis. In: International Conference on Learning Representations, ICLR (2024). https:\/\/openreview.net\/forum?id=di52zR8xgf"},{"key":"4075_CR20","doi-asserted-by":"publisher","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: IEEE\/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023, pp. 3813\u20133824 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00355","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"4075_CR21","doi-asserted-by":"publisher","unstructured":"Saharia, C., Chan, W., Chang, H., Lee, C.A., Ho, J., Salimans, T., Fleet, D.J., Norouzi, M.: Palette: Image-to-image diffusion models. In: SIGGRAPH \u201922: Special Interest Group on Computer Graphics and Interactive Techniques Conference, pp. 15\u201311510 (2022). https:\/\/doi.org\/10.1145\/3528233.3530757","DOI":"10.1145\/3528233.3530757"},{"issue":"5","key":"4075_CR22","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1016\/J.VRIH.2022.08.007","volume":"4","author":"Y Zhao","year":"2022","unstructured":"Zhao, Y., Zhang, H., Lu, P., Li, P., Wu, E., Sheng, B.: DSD-MatchingNet: deformable sparse-to-dense feature matching for learning accurate correspondences. Virtual Real. Intell. Hardw. 4(5), 432\u2013443 (2022). https:\/\/doi.org\/10.1016\/J.VRIH.2022.08.007","journal-title":"Virtual Real. Intell. Hardw."},{"issue":"4","key":"4075_CR23","doi-asserted-by":"publisher","first-page":"5613","DOI":"10.1109\/TITS.2025.3539627","volume":"26","author":"X Tan","year":"2025","unstructured":"Tan, X., Wu, W., Zhang, Z., Fan, C., Peng, Y., Zhang, Z., Xie, Y., Ma, L.: GEOcc: geometrically enhanced 3d occupancy network with implicit-explicit depth fusion and contextual self-supervision. IEEE Trans. Intell. Transp. Syst. 26(4), 5613\u20135623 (2025). https:\/\/doi.org\/10.1109\/TITS.2025.3539627","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"12","key":"4075_CR24","doi-asserted-by":"publisher","first-page":"15328","DOI":"10.1109\/TPAMI.2023.3319470","volume":"45","author":"X Tan","year":"2023","unstructured":"Tan, X., Ma, Q., Gong, J., Xu, J., Zhang, Z., Song, H., Qu, Y., Xie, Y., Ma, L.: Positive-negative receptive field reasoning for omni-supervised 3d segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 45(12), 15328\u201315344 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3319470","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4075_CR25","doi-asserted-by":"publisher","unstructured":"Xie, Z., Li, H., Ding, H., Li, M., Di, X., Cao, Y.: Hierafashdiff: Hierarchical fashion design with multi-stage diffusion models. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 8762\u20138770 (2025). https:\/\/doi.org\/10.1609\/AAAI.V39I8.32947","DOI":"10.1609\/AAAI.V39I8.32947"},{"issue":"1","key":"4075_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/J.VRIH.2022.11.001","volume":"5","author":"C Hoshizawa","year":"2023","unstructured":"Hoshizawa, C., Komuro, T.: View interpolation networks for reproducing material appearance of specular objects. Virtual Real. Intell. Hardw. 5(1), 1\u201310 (2023). https:\/\/doi.org\/10.1016\/J.VRIH.2022.11.001","journal-title":"Virtual Real. Intell. Hardw."},{"issue":"5","key":"4075_CR27","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1016\/J.VRIH.2022.08.003","volume":"4","author":"N Mishra","year":"2022","unstructured":"Mishra, N., Ramanathan, M., Tulsulkar, G., Magnenat-Thalmann, N.: Uncanny valley for interactive social agents: an experimental study. Virtual Real. Intell. Hardw. 4(5), 393\u2013405 (2022). https:\/\/doi.org\/10.1016\/J.VRIH.2022.08.003","journal-title":"Virtual Real. Intell. Hardw."},{"issue":"1","key":"4075_CR28","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/J.VRIH.2022.07.007","volume":"5","author":"H Liang","year":"2023","unstructured":"Liang, H., Li, J., Wang, Y., Pan, J., Zhang, Y., Dong, X.: Metaverse virtual social center for the elderly communication during the social distancing. Virtual Real. Intell. Hardw. 5(1), 68\u201380 (2023). https:\/\/doi.org\/10.1016\/J.VRIH.2022.07.007","journal-title":"Virtual Real. Intell. Hardw."},{"key":"4075_CR29","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 28, pp. 2017\u20132025 (2015)"},{"key":"4075_CR30","doi-asserted-by":"publisher","unstructured":"Isola, P., Zhu, J., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5967\u20135976 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.632","DOI":"10.1109\/CVPR.2017.632"},{"issue":"4","key":"4075_CR31","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.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004). https:\/\/doi.org\/10.1109\/TIP.2003.819861","journal-title":"IEEE Trans. Image Process."},{"key":"4075_CR32","doi-asserted-by":"publisher","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Proceedings of the European Conference on Computer Vision (ECCV). Lecture Notes in Computer Science, vol. 9906, pp. 694\u2013711 (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"4075_CR33","doi-asserted-by":"publisher","unstructured":"Jiang, L., Dai, B., Wu, W., Loy, C.C.: Focal frequency loss for image reconstruction and synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 13899\u201313909 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.01366","DOI":"10.1109\/ICCV48922.2021.01366"},{"key":"4075_CR34","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations, ICLR (2019). https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"4075_CR35","doi-asserted-by":"publisher","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 586\u2013595 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00068","DOI":"10.1109\/CVPR.2018.00068"},{"key":"4075_CR36","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 (NeurIPS), vol. 30, pp. 6626\u20136637 (2017)"},{"key":"4075_CR37","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying mmd gans. In: International Conference on Learning Representations (ICLR) (2018). https:\/\/openreview.net\/forum?id=r1lUOzWCW"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04075-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-04075-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04075-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T13:59:30Z","timestamp":1758722370000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-04075-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,29]]},"references-count":37,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["4075"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-04075-5","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2025,6,29]]},"assertion":[{"value":"17 June 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 June 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}