{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:12:24Z","timestamp":1778051544928,"version":"3.51.4"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00028","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"202-211","source":"Crossref","is-referenced-by-count":0,"title":["DiT-VTON: Diffusion Transformer Framework for Unified Multi-Category Virtual Try-On and Virtual Try-All with Integrated Image Editing"],"prefix":"10.1109","author":[{"given":"Qi","family":"Li","sequence":"first","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuwen","family":"Qiu","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles (UCLA)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kee Kiat","family":"Koo","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julien","family":"Han","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karim","family":"Bouyarmane","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref3","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00781"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_13"},{"key":"ref8","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref9","article-title":"Efficient encoder-free pose conditioning and pose control for virtual try-on","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","author":"Li"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00313"},{"key":"ref11","article-title":"Instructv-ton: Optimal auto-masking and natural-language-guided interactive style control for inpainting-based virtual try-on","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","author":"Han"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00838"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_13"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02255"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00447"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00670"},{"key":"ref19","article-title":"Catvton: Concatenation is all you need for virtual try-on with diffusion models","author":"Chong","year":"2024"},{"key":"ref20","article-title":"Anyfit: Controllable virtual try-on for any combination of attire across any scenario","author":"Li","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32827"},{"key":"ref22","article-title":"Mmtryon: Multi-modal multi-reference control for high-quality fashion generation","author":"Zhang","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00134"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_8"},{"key":"ref25","article-title":"Diffuse to choose: Enriching image conditioned inpainting in latent diffusion models for virtual try-all","author":"Seyfioglu","year":"2024"},{"key":"ref26","article-title":"Dreampaint: Few-shot inpainting of e-commerce items for virtual try-on without 3d modeling","author":"Seyfioglu","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02458"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref29","first-page":"18310","article-title":"Object-stitch: Object compositing with diffusion model","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Song"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2669"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref33","article-title":"Viton-dit: Learning in-the-wild video try-on from human dance videos via diffusion transformers","author":"Zheng","year":"2024"},{"key":"ref35","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref36","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/978-3-030-70679-1_5","article-title":"Variational autoencoder","volume-title":"Variational Methods for Machine Learning with Applications to Deep Networks","author":"Cinelli","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612137"},{"key":"ref39","article-title":"Oot-diffusion: Outfitting fusion based latent diffusion for controllable virtual try-on","author":"Xu","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref43","article-title":"Transfusion: Predict the next token and diffuse images with one multi-modal model","author":"Zhou","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00243"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref47","article-title":"Demystifying mmd gans","author":"Bi\u0144kowski","year":"2018"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492554.pdf?arnumber=11492554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:17:17Z","timestamp":1778048237000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492554\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00028","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}