{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T23:02:52Z","timestamp":1789686172077,"version":"4.0.1"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370310","type":"print"},{"value":"9783032370327","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37032-7_34","type":"book-chapter","created":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T22:14:38Z","timestamp":1789683278000},"page":"626-643","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["WearWow: Native 2K Multi-garment Virtual Try-On via\u00a0Adaptive Token Packing and\u00a0Preference Alignment"],"prefix":"10.1007","author":[{"given":"Xujie","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runyan","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongliang","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liping","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luo","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaochao","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luoqi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"key":"34_CR1","unstructured":"Achiam, J., et al.: GPT-4 Technical Report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Bai, S., Zhou, H., Li, Z., Zhou, C., Yang, H.: Single stage virtual try-on via deformable attention flows. In: European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-19784-0_24"},{"key":"34_CR3","unstructured":"Betker, J., et\u00a0al.: Improving image generation with better captions. Comput. Sci. 2(3), 8 (2023). https:\/\/cdnopenai.com\/papers\/dall-e-3.pdf"},{"key":"34_CR4","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying MMD GANs (2021). https:\/\/arxiv.org\/abs\/1801.01401"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Huang, L., Liu, Y., Shen, Y., Zhao, D., Zhao, H.: AnyDoor: zero-shot object-level image customization. arXiv preprint arXiv:2307.09481 (2023)","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"34_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 Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"34_CR7","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. arXiv preprint arXiv:2403.05139 (2024)","DOI":"10.1007\/978-3-031-73016-0_13"},{"key":"34_CR8","unstructured":"Chong, Z., et al.: CatVTON: concatenation is all you need for virtual try-on with diffusion models (2024). https:\/\/arxiv.org\/abs\/2407.15886"},{"key":"34_CR9","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 (2021)","DOI":"10.1109\/ICCV48922.2021.01437"},{"key":"34_CR10","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 (2019)","DOI":"10.1109\/ICCV.2019.00912"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: Dressing in the wild by watching dance videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00347"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Feng, Y., et al.: OmniTry: virtual try-on anything without masks. arXiv preprint arXiv:2508.13632 (2025)","DOI":"10.52202\/085713-4419"},{"key":"34_CR13","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 (2021)","DOI":"10.1109\/CVPR46437.2021.00838"},{"key":"34_CR14","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 (2023)","DOI":"10.1145\/3581783.3612255"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Guo, H., Zeng, B., Song, Y., Zhang, W., Liu, J., Zhang, C.: Any2anytryon: leveraging adaptive position embeddings for versatile virtual clothing tasks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19085\u201319096 (2025)","DOI":"10.1109\/ICCV51701.2025.01774"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"He, S., Song, Y.Z., Xiang, T.: Style-based global appearance flow for virtual try-on, CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00346"},{"key":"34_CR17","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)"},{"key":"34_CR18","unstructured":"Huang, L., Chen, D., Liu, Y., Shen, Y., Zhao, D., Zhou, J.: Composer: creative and controllable image synthesis with composable conditions. arXiv preprint arXiv:2302.09778 (2023)"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Kim, J., Jin, H., Park, S., Choo, J.: Promptdresser: improving the quality and controllability of virtual try-on via generative textual prompt and prompt-aware mask (2024). https:\/\/arxiv.org\/abs\/2412.16978","DOI":"10.1109\/ICCV51701.2025.01487"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Lee, S., Gu, G., Park, S., Choi, S., Choo, J.: High-resolution virtual try-on with misalignment and occlusion-handled conditions. In: European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-19790-1_13"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Li, G., et al.: Cascaded diffusion models for virtual try-on: improving control and resolution. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 4689\u20134697 (2025)","DOI":"10.1609\/aaai.v39i5.32495"},{"key":"34_CR22","doi-asserted-by":"crossref","unstructured":"Lin, E., et al.: DreamFit: garment-centric human generation via a lightweight anything-dressing encoder. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 5218\u20135226. AAAI (2025)","DOI":"10.1609\/aaai.v39i5.32554"},{"key":"34_CR23","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: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2020)"},{"key":"34_CR24","doi-asserted-by":"crossref","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 ACM International Conference on Multimedia (2023)","DOI":"10.1145\/3581783.3612137"},{"key":"34_CR25","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 (2022)","DOI":"10.1007\/978-3-031-20074-8_20"},{"key":"34_CR26","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)"},{"key":"34_CR27","doi-asserted-by":"publisher","first-page":"53728","DOI":"10.52202\/075280-2338","volume":"36","author":"R Rafailov","year":"2023","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: your language model is secretly a reward model. Adv. Neural. Inf. Process. Syst. 36, 53728\u201353741 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"34_CR28","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"34_CR29","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 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"34_CR30","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding (2022)","DOI":"10.52202\/068431-2643"},{"key":"34_CR31","doi-asserted-by":"publisher","first-page":"36479","DOI":"10.52202\/068431-2643","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"34_CR32","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"34_CR33","unstructured":"Seedream, T., et\u00a0al.: Seedream 4.0: toward next-generation multimodal image generation. arXiv preprint arXiv:2509.20427 (2025)"},{"key":"34_CR34","unstructured":"Seitzer, M.: pytorch-fid: FID Score for PyTorch (2020). https:\/\/github.com\/mseitzer\/pytorch-fid. Version 0.3.0"},{"key":"34_CR35","doi-asserted-by":"crossref","unstructured":"Shen, F., et al.: IMAGDressing-v1: customizable virtual dressing (2024)","DOI":"10.1609\/aaai.v39i7.32729"},{"key":"34_CR36","unstructured":"Shen, X., et al.: Directly aligning the full diffusion trajectory with fine-grained human preference. arXiv preprint arXiv:2509.06942 (2025)"},{"key":"34_CR37","unstructured":"Team, K., et\u00a0al.: Kling-Omni Technical Report. arXiv preprint arXiv:2512.16776 (2025)"},{"key":"34_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1007\/978-3-030-01261-8_36","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Wang","year":"2018","unstructured":"Wang, B., Zheng, H., Liang, X., Chen, Y., Lin, L., Yang, M.: Toward Characteristic-Preserving Image-Based Virtual Try-On Network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 607\u2013623. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_36"},{"issue":"4","key":"34_CR39","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":"34_CR40","unstructured":"Wu, C., et\u00a0al.: Qwen-Image Technical Report. arXiv preprint arXiv:2508.02324 (2025)"},{"key":"34_CR41","unstructured":"Wu, X., et al.: Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis. arXiv preprint arXiv:2306.09341 (2023)"},{"key":"34_CR42","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: GP-VTON: towards general purpose virtual try-on via collaborative local-flow global-parsing learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.02255"},{"key":"34_CR43","unstructured":"Xie, Z., et al.: PASTA-GAN++: a versatile framework for high-resolution unpaired virtual try-on. arXiv preprint arXiv:2207.13475 (2022)"},{"key":"34_CR44","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: WAS-VTON: warping architecture search for virtual try-on network. In: Proceedings of the 29th ACM International Conference on Multimedia (2021)","DOI":"10.1145\/3474085.3475490"},{"key":"34_CR45","doi-asserted-by":"crossref","unstructured":"Xu, Y., Gu, T., Chen, W., Chen, C.: OOTDiffusion: outfitting fusion based latent diffusion for controllable virtual try-on. arXiv preprint arXiv:2403.01779 (2024)","DOI":"10.1609\/aaai.v39i9.32973"},{"key":"34_CR46","unstructured":"Yang, A., et\u00a0al.: Qwen3 Technical Report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"34_CR47","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 (2023)","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"34_CR48","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 (2020)","DOI":"10.1109\/CVPR42600.2020.00787"},{"key":"34_CR49","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":"34_CR50","unstructured":"Zhang, X., et al.: MMTryon: multi-modal multi-reference control for high-quality fashion generation (2024). https:\/\/arxiv.org\/abs\/2405.00448"},{"key":"34_CR51","unstructured":"Zhou, Z., et al.: Learning flow fields in attention for controllable person image generation. arXiv preprint arXiv:2412.08486 (2024)"},{"key":"34_CR52","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 (2023)","DOI":"10.1109\/CVPR52729.2023.00447"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37032-7_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T22:14:48Z","timestamp":1789683288000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37032-7_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370310","9783032370327"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37032-7_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"18 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}