{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:39:53Z","timestamp":1771922393010,"version":"3.50.1"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccvw69036.2025.00210","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:44:02Z","timestamp":1771879442000},"page":"2006-2015","source":"Crossref","is-referenced-by-count":0,"title":["MFT-VITON: High-Fidelity Virtual Try-On with Minimal Input via a Mask-Free Transformer-Diffusion Model"],"prefix":"10.1109","author":[{"given":"Zhenchen","family":"Wan","sequence":"first","affiliation":[{"name":"University of Melbourne"}]},{"given":"Yanwu","family":"Xu","sequence":"additional","affiliation":[{"name":"Google"}]},{"given":"Dongting","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Melbourne"}]},{"given":"Weilun","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of Melbourne"}]},{"given":"Tianxi","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Melbourne"}]},{"given":"Zhaoqing","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Sydney"}]},{"given":"Feng","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Melbourne"}]},{"given":"Tongliang","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Sydney"}]},{"given":"Mingming","family":"Gong","sequence":"additional","affiliation":[{"name":"University of Melbourne"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480559"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_24"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00552"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00145"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00125"},{"key":"ref8","volume-title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","author":"Esser","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00757"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612255"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00787"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref13","article-title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","volume-title":"Advances in Neural Information Processing Systems","author":"Heusel","year":"2017"},{"key":"ref14","volume-title":"VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss","author":"Honda","year":"2019"},{"key":"ref15","volume-title":"U-GA T-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation","author":"Kim","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00781"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67070-2_17"},{"key":"ref18","volume-title":"Flux","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_13"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3029455"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00199"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00600"},{"key":"ref23","volume-title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","author":"Liu","year":"2022"},{"key":"ref24","article-title":"Pose Guided Person Image Generation","volume-title":"Advances in Neural Information Processing Systems","author":"Ma","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00513"},{"key":"ref26","volume-title":"CP-VTON+: Clothing Shape and Texture Preserving Image-Based Virtual Try-On","author":"Minar","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00243"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612137"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00666"},{"key":"ref30","volume-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956089"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412908"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref35","volume-title":"SeedEdit: Align Image Re-Generation to Image Editing","author":"Shi","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28288"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72967-6_11"},{"key":"ref38","volume-title":"TED-VITON: Transformer-Empowered Diffusion Models for Virtual Try-On","author":"Wan","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02255"},{"key":"ref42","volume-title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","author":"Ye","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02458"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_10"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00447"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00134"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00245"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,20]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373940\/11374285\/11375578.pdf?arnumber=11375578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:34:53Z","timestamp":1771918493000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11375578\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccvw69036.2025.00210","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}