{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T15:00:40Z","timestamp":1783350040267,"version":"3.54.6"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T00:00:00Z","timestamp":1711584000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T00:00:00Z","timestamp":1711584000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971339"],"award-info":[{"award-number":["61971339"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017596","name":"Natural Science Basic Research Program of Shaanxi Province","doi-asserted-by":"publisher","award":["2023-JC-YB-826"],"award-info":[{"award-number":["2023-JC-YB-826"]}],"id":[{"id":"10.13039\/501100017596","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Scientific Research Program Funded by Shaanxi Provincial Education Department","award":["22JP028"],"award-info":[{"award-number":["22JP028"]}]},{"name":"Joint Foundation of Shaanxi Computer Society and Xi\u2019an Xiangteng Microelectronics Technology Co., Ltd"},{"name":"Technology Guidance Program of China National Textile and Apparel Council","award":["2020100"],"award-info":[{"award-number":["2020100"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s00371-024-03347-w","type":"journal-article","created":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T18:03:09Z","timestamp":1711648989000},"page":"563-577","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["CS-VITON: a realistic virtual try-on network based on clothing region alignment and SPM"],"prefix":"10.1007","volume":"41","author":[{"given":"Jinguang","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lili","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaibing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,28]]},"reference":[{"issue":"8","key":"3347_CR1","doi-asserted-by":"publisher","first-page":"9801","DOI":"10.1007\/s13369-021-06348-2","volume":"47","author":"A Singh","year":"2022","unstructured":"Singh, A., Satapathy, S.C., Roy, A., Gutub, A.: AI-based mobile edge computing for IoT: applications, challenges, and future scope. Arab. J. Sci. Eng. 47(8), 9801\u20139831 (2022)","journal-title":"Arab. J. Sci. Eng."},{"issue":"7","key":"3347_CR2","first-page":"11","volume":"16","author":"N Farooqi","year":"2019","unstructured":"Farooqi, N., Gutub, A., Khozium, M.O.: Smart community challenges: enabling IoT\/M2M technology case study. Life Sci. J. 16(7), 11\u201317 (2019)","journal-title":"Life Sci. J."},{"key":"3347_CR3","doi-asserted-by":"publisher","unstructured":"Bertiche, H., Madadi, M., Escalera, S.: CLOTH3D: clothed 3D humans. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) Computer Vision\u2014ECCV 2020, vol. 12365, pp. 344\u2013359. Springer International Publishing, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_21","DOI":"10.1007\/978-3-030-58565-5_21"},{"key":"3347_CR4","doi-asserted-by":"crossref","unstructured":"Zhao, F., Xie, Z., Kampffmeyer, M., Dong, H., Han, S., Zheng, T., Zhang, T., Liang, X.: M3d-vton: a monocular-to-3d virtual try-on network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13239\u201313249 (2021)","DOI":"10.1109\/ICCV48922.2021.01299"},{"key":"3347_CR5","doi-asserted-by":"crossref","unstructured":"Santesteban, I., Thuerey, N., Otaduy, M.A., Casas, D.: Self-supervised collision handling via generative 3d garment models for virtual try-on. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11763\u201311773 (2021)","DOI":"10.1109\/CVPR46437.2021.01159"},{"key":"3347_CR6","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":"3347_CR7","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: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision\u2014ECCV 2022, vol. 13677, pp. 204\u2013219. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_13","DOI":"10.1007\/978-3-031-19790-1_13"},{"key":"3347_CR8","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.-Y., Wang, T.-C., Zhu, J.-Y.: Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2337\u20132346 (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"3347_CR9","doi-asserted-by":"publisher","unstructured":"Luo, W., Yang, S., Wang, H., Long, B., Zhang, W.: Context-consistent semantic image editing with style-preserved modulation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision\u2014ECCV 2022, vol. 13677, pp. 561\u2013578. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_34","DOI":"10.1007\/978-3-031-19790-1_34"},{"key":"3347_CR10","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"},{"issue":"6","key":"3347_CR11","doi-asserted-by":"publisher","first-page":"3260","DOI":"10.1109\/TPAMI.2020.3048039","volume":"44","author":"P Li","year":"2020","unstructured":"Li, P., Xu, Y., Wei, Y., Yang, Y.: Self-correction for human parsing. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 3260\u20133271 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3347_CR12","doi-asserted-by":"publisher","first-page":"5599","DOI":"10.1109\/TIP.2022.3192989","volume":"31","author":"S Zhang","year":"2022","unstructured":"Zhang, S., Cao, X., Qi, G.-J., Song, Z., Zhou, J.: Aiparsing: anchor-free instance-level human parsing. IEEE Trans. Image Process. 31, 5599\u20135612 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"3347_CR13","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.-E., Sheikh, Y.: Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"3347_CR14","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"},{"issue":"5","key":"3347_CR15","doi-asserted-by":"publisher","first-page":"2005","DOI":"10.1007\/s00371-022-02460-y","volume":"39","author":"J Xu","year":"2023","unstructured":"Xu, J., Liu, W., Xing, W., Wei, X.: MSPENet: multi-scale adaptive fusion and position enhancement network for human pose estimation. Vis. Comput. 39(5), 2005\u20132019 (2023). https:\/\/doi.org\/10.1007\/s00371-022-02460-y","journal-title":"Vis. Comput."},{"issue":"1","key":"3347_CR16","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1007\/s00371-021-02339-4","volume":"39","author":"K Wang","year":"2023","unstructured":"Wang, K., Zhang, G., Yang, J.: 3D human pose and shape estimation with dense correspondence from a single depth image. Vis. Comput. 39(1), 429\u2013441 (2023). https:\/\/doi.org\/10.1007\/s00371-021-02339-4","journal-title":"Vis. Comput."},{"key":"3347_CR17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3192661","author":"W Tang","year":"2022","unstructured":"Tang, W., He, F., Liu, Y.: YDTR: infrared and visible image fusion via Y-shape dynamic transformer. IEEE Trans. Multimed. (2022). https:\/\/doi.org\/10.1109\/TMM.2022.3192661","journal-title":"IEEE Trans. Multimed."},{"key":"3347_CR18","doi-asserted-by":"crossref","unstructured":"Kang, M., Zhu, J.-Y., Zhang, R., Park, J., Shechtman, E., Paris, S., Park, T.: Scaling up GANs for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10124\u201310134 (2023)","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"3347_CR19","doi-asserted-by":"publisher","first-page":"5134","DOI":"10.1109\/TIP.2022.3193288","volume":"31","author":"W Tang","year":"2022","unstructured":"Tang, W., He, F., Liu, Y., Duan, Y.: MATR: multimodal medical image fusion via multiscale adaptive transformer. IEEE Trans. Image Process. 31, 5134\u20135149 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"3347_CR20","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27, 2672\u20132680 (2014)"},{"key":"3347_CR21","unstructured":"Mirza, M., Osindero, S.: Conditional Generative Adversarial Nets. arXiv:1411.1784 (2014)"},{"key":"3347_CR22","doi-asserted-by":"crossref","unstructured":"Wang, T.-C., Liu, M.-Y., Zhu, J.-Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8798\u20138807 (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"3347_CR23","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F.F. (eds.) Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015, vol. 9351, pp. 234\u2013241. Springer International Publishing, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"2","key":"3347_CR24","doi-asserted-by":"publisher","first-page":"141","DOI":"10.3233\/ICA-210672","volume":"29","author":"H Wu","year":"2022","unstructured":"Wu, H., He, F., Duan, Y., Yan, X.: Perceptual metric-guided human image generation. Integr. Comput. Aided Eng. 29(2), 141\u2013151 (2022)","journal-title":"Integr. Comput. Aided Eng."},{"key":"3347_CR25","doi-asserted-by":"crossref","unstructured":"Jetchev, N., Bergmann, U.: The conditional analogy GAN: swapping fashion articles on people images. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 2287\u20132292 (2017)","DOI":"10.1109\/ICCVW.2017.269"},{"key":"3347_CR26","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":"3347_CR27","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"},{"issue":"6","key":"3347_CR28","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1109\/34.24792","volume":"11","author":"FL Bookstein","year":"1989","unstructured":"Bookstein, F.L.: Principal warps: thin-plate splines and the decomposition of deformations. IEEE Trans. Pattern Anal. Mach. Intell. 11(6), 567\u2013585 (1989)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3347_CR29","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":"3347_CR30","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":"3347_CR31","doi-asserted-by":"publisher","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.) Computer Vision\u2014ECCV 2016, vol. 9908, pp. 286\u2013301. Springer International Publishing, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_18","DOI":"10.1007\/978-3-319-46493-0_18"},{"key":"3347_CR32","doi-asserted-by":"crossref","unstructured":"Baldrati, A., Morelli, D., Cartella, G., Cornia, M., Bertini, M., Cucchiara, R.: Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing. arXiv:2304.02051 (2023)","DOI":"10.1109\/ICCV51070.2023.02138"},{"key":"3347_CR33","doi-asserted-by":"crossref","unstructured":"Chen, C.-Y., Chen, Y.-C., Shuai, H.-H., Cheng, W.-H.: Size does matter: size-aware virtual try-on via clothing-oriented transformation try-on network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7513\u20137522 (2023)","DOI":"10.1109\/ICCV51070.2023.00691"},{"key":"3347_CR34","doi-asserted-by":"crossref","unstructured":"Gong, K., Liang, X., Li, Y., Chen, Y., Yang, M., Lin, L.: Instance-level human parsing via part grouping network. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 770\u2013785 (2018)","DOI":"10.1007\/978-3-030-01225-0_47"},{"key":"3347_CR35","doi-asserted-by":"publisher","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.) Computer Vision\u2014ECCV 2016, vol. 9906, pp. 694\u2013711. Springer International Publishing, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"3347_CR36","unstructured":"Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:1409.1556 (2015)"},{"key":"3347_CR37","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)"},{"key":"3347_CR38","doi-asserted-by":"crossref","unstructured":"Mao, X., Li, Q., Xie, H., Lau, R.Y., Wang, Z., Paul\u00a0Smolley, S.: Least squares generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2794\u20132802 (2017)","DOI":"10.1109\/ICCV.2017.304"},{"key":"3347_CR39","unstructured":"Lim, J.H., Ye, J.C.: Geometric GAN. arXiv:1705.02894 (2017)"},{"key":"3347_CR40","unstructured":"Kingma, D.P., Ba, J.: Adam: A Method for Stochastic Optimization. arXiv:1412.6980 (2017)"},{"issue":"4","key":"3347_CR41","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)","journal-title":"IEEE Trans. Image Process."},{"key":"3347_CR42","doi-asserted-by":"crossref","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 Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"3347_CR43","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. Adv. Neural Inf. Process. Syst. 30, 6629\u20136640 (2017)"},{"key":"3347_CR44","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying MMD GANs. arXiv:1801.01401 (2021)"},{"key":"3347_CR45","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. Adv. Neural Inf. Process. Syst. 29, 2234\u20132242 (2016)"},{"key":"3347_CR46","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03347-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03347-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03347-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T22:54:56Z","timestamp":1737759296000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03347-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,28]]},"references-count":46,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["3347"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03347-w","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,28]]},"assertion":[{"value":"26 February 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 March 2024","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 have no conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Informed consent was obtained from all individual participants included in the study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}}]}}