{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T04:02:45Z","timestamp":1784001765407,"version":"3.55.0"},"reference-count":38,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62436009,62276258"],"award-info":[{"award-number":["62436009,62276258"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01723","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18542-18551","source":"Crossref","is-referenced-by-count":1,"title":["HiGarment: Cross-Modal Harmony Based Diffusion Model for Flat Sketch to Realistic Garment Image"],"prefix":"10.1109","author":[{"given":"Junyi","family":"Guo","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong Liverpool University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingxuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong Liverpool University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangyu","family":"Wu","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong Liverpool University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huanda","family":"Lu","sequence":"additional","affiliation":[{"name":"NingboTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiufeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong Liverpool University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenmian","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eng Gee","family":"Lim","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong Liverpool University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongming","family":"Lu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/s40691-021-00262-9"},{"key":"ref2","article-title":"Mllm-as-a-judge: Assessing multimodal 11 m -as-a-judge with vision-language benchmark","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-50072-5_36"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"ref5","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72111-3_24"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00269"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00787"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3658147"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref11","first-page":"6629","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3456442"},{"key":"ref14","article-title":"Blip-diffusion: Pretrained subject representation for controllable text-to-image generation and editing","author":"Li","year":"2024","journal-title":"NeurIPS"},{"key":"ref15","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3178991"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191565"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00268"},{"key":"ref19","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref20","article-title":"U-mamba: Enhancing long-range dependency for biomedical image segmentation","author":"Ma","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00830"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"ref27","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2013.2296554"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00713"},{"key":"ref30","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_9"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548230"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02116"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/NICOInt62634.2024.00021"},{"key":"ref38","volume":"36","author":"Zhao","year":"2024","journal-title":"NeurIPS"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445203.pdf?arnumber=11445203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:23:21Z","timestamp":1777530201000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445203\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01723","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}