{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T06:46:00Z","timestamp":1785653160712,"version":"3.56.0"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032316622","type":"print"},{"value":"9783032316639","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"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":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-31663-9_22","type":"book-chapter","created":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:48:31Z","timestamp":1785649711000},"page":"327-342","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["What Matters in\u00a0Virtual Try-Off? Dual-UNet Diffusion Models for\u00a0Garment Reconstruction"],"prefix":"10.1007","author":[{"given":"Loc-Phat","family":"Truong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meysam","family":"Madadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergio","family":"Escalera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"22_CR1","unstructured":"Berrada, T., et al.: Boosting latent diffusion with perceptual objectives. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"22_CR2","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":"22_CR3","doi-asserted-by":"crossref","unstructured":"Choi, Y., Kwak, S., Lee, K., Choi, H., Shin, J.: Improving Diffusion Models for Authentic Virtual Try-on in the Wild. In: Computer Vision \u2013 ECCV 2024, vol. 15144, pp. 206\u2013235. Springer Nature Switzerland, Cham (2025). Lecture Notes in Computer Science","DOI":"10.1007\/978-3-031-73016-0_13"},{"key":"22_CR4","unstructured":"Chong, Z., et\u00a0al.: Catvton: concatenation is all you need for virtual try-on with diffusion models. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Cui, A., McKee, D., Lazebnik, S.: Dressing in order: Recurrent person image generation for pose transfer, virtual try-on and outfit editing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14638\u201314647 (2021)","DOI":"10.1109\/ICCV48922.2021.01437"},{"key":"22_CR6","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Gou, J., Sun, S., Zhang, J., Si, J., Qian, C., Zhang, L.: Taming the power of diffusion models for high-quality virtual try-on with appearance flow. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 7599\u20137607 (2023)","DOI":"10.1145\/3581783.3612255"},{"key":"22_CR8","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":"22_CR9","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: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7543\u20137552 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00787. ISSN: 2575-7075","DOI":"10.1109\/CVPR.2018.00787"},{"key":"22_CR10","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR11","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":"22_CR12","doi-asserted-by":"crossref","unstructured":"Kang, M., et al.: Distilling Diffusion Models into Conditional GANs. In: European Conference on Computer Vision (ECCV) (2024)","DOI":"10.1007\/978-3-031-73390-1_25"},{"key":"22_CR13","doi-asserted-by":"publisher","unstructured":"Kim, J., Gu, G., Park, M., Park, S., Choo, J.: Stable VITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8176\u20138185. IEEE, Seattle, WA, USA (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.00781","DOI":"10.1109\/CVPR52733.2024.00781"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Lee, H.J., Lee, R., Kang, M., Cho, M., Park, G.: La-viton: a network for looking-attractive virtual try-on. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp.\u00a00\u20130 (2019)","DOI":"10.1109\/ICCVW.2019.00381"},{"key":"22_CR15","unstructured":"Lipman, Y., Chen, R.T.Q., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=PqvMRDCJT9t"},{"key":"22_CR16","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"22_CR17","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Morelli, D., Baldrati, A., Cartella, G., Cornia, M., Bertini, M., Cucchiara, R.: Ladivton: latent diffusion textual-inversion enhanced virtual try-on. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 8580\u20138589 (2023)","DOI":"10.1145\/3581783.3612137"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Morelli, D., Fincato, M., Cornia, M., Landi, F., Cesari, F., Cucchiara, R.: Dress Code: High-Resolution Multi-Category Virtual Try-On. In: Proceedings of the European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-20074-8_20"},{"key":"22_CR20","doi-asserted-by":"publisher","unstructured":"Mou, C., et al.: T2iadapter: learning adapters to dig out more controllable ability for text-toimage diffusion models. In: Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence. AAAI\u20192024\/IAAI\u201924\/EAAI\u201924, AAAI Press (2024). https:\/\/doi.org\/10.1609\/aaai.v38i5.28226","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"22_CR22","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"22_CR23","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"22_CR24","doi-asserted-by":"crossref","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, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"22_CR25","doi-asserted-by":"publisher","unstructured":"Shen, L., Huang, R., Wang, Z.: IGR: Improving Diffusion Model for Garment Restoration from Person Image (2024). https:\/\/doi.org\/10.48550\/arXiv.2412.11513, arXiv:2412.11513","DOI":"10.48550\/arXiv.2412.11513"},{"key":"22_CR26","unstructured":"Unsplash: Unsplash - the internet\u2019s source of free stock photos and images. https:\/\/unsplash.com\/ (Accessed 29 Nov 2025)"},{"key":"22_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"22_CR28","doi-asserted-by":"publisher","unstructured":"Velioglu, R., Bevandic, P., Chan, R., Hammer, B.: TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models (2024). https:\/\/doi.org\/10.48550\/arXiv.2411.18350, arXiv:2411.18350","DOI":"10.48550\/arXiv.2411.18350"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Wang, B., Zheng, H., Liang, X., Chen, Y., Lin, L., Yang, M.: Toward characteristicpreserving 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":"22_CR30","unstructured":"Wang, C., et al.: FLDM-VTON: faithful latent diffusion model for virtual try-on. arXiv preprint arXiv:2404.14162 (2024)"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: FW-VTON: flattening-and-warping for person-to-person virtual try-on. arXiv preprint arXiv:2507.16010 (2025)","DOI":"10.1109\/ICASSP55912.2026.11464329"},{"key":"22_CR32","doi-asserted-by":"publisher","unstructured":"Xarchakos, I., Koukopoulos, T.: TryOffAnyone: Tiled Cloth Generation from a Dressed Person (2025). https:\/\/doi.org\/10.48550\/arXiv.2412.08573, arXiv:2412.08573","DOI":"10.48550\/arXiv.2412.08573"},{"key":"22_CR33","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 Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence and Fifteenth Symposium on Educational Advances in Artificial Intelligence. AAAI\u20192025\/IAAI\u201925\/EAAI\u20192025, AAAI Press (2025). https:\/\/doi.org\/10.1609\/aaai.v39i9.32973","DOI":"10.1609\/aaai.v39i9.32973"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Yang, B., et al.: Paint by example: exemplar-based image editing with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18381\u201318391 (2023)","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"22_CR35","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: Ip-adapter: text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)"},{"key":"22_CR36","doi-asserted-by":"publisher","first-page":"17587","DOI":"10.1007\/s00521-020-04928-1","volume":"32","author":"W Zeng","year":"2020","unstructured":"Zeng, W., Zhao, M., Gao, Y., Zhang, Z.: Tilegan: category-oriented attention-based high-quality tiled clothes generation from dressed person. Neural Comput. Appl. 32, 17587\u201317600 (2020)","journal-title":"Neural Comput. Appl."},{"key":"22_CR37","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"22_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"22_CR39","doi-asserted-by":"publisher","unstructured":"Zhang, N., et al.: Viton-gun: person-to-person virtual try-on via garment unwrapping. IEEE Transactions on Visualization and Computer Graphics pp. 1\u201313 (2025). https:\/\/doi.org\/10.1109\/TVCG.2025.3550776","DOI":"10.1109\/TVCG.2025.3550776"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, Z., et\u00a0al.: Learning flow fields in attention for controllable person image generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2491\u20132501 (2025)","DOI":"10.1109\/CVPR52734.2025.00238"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Zhu, L., et al.: Tryondiffusion: a tale of two UNets. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4606\u20134615 (2023)","DOI":"10.1109\/CVPR52729.2023.00447"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31663-9_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:48:35Z","timestamp":1785649715000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31663-9_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"ISBN":["9783032316622","9783032316639"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31663-9_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]},"assertion":[{"value":"3 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}