{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:54:52Z","timestamp":1777888492903,"version":"3.51.4"},"reference-count":67,"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\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["25ZR1401187"],"award-info":[{"award-number":["25ZR1401187"]}],"id":[{"id":"10.13039\/501100003399","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\/iccv51701.2025.01624","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17485-17495","source":"Crossref","is-referenced-by-count":0,"title":["RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilation"],"prefix":"10.1109","author":[{"given":"Yuhan","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianfeng","family":"Tan","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxiang","family":"Shang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yubo","family":"Wu","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuanhong","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hangcheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingbing","family":"Ni","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1227983"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1114"},{"key":"ref5","first-page":"2206","article-title":"Improving language models by retrieving from trillions of tokens","volume-title":"International conference on machine learning","author":"Borgeaud","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2023.104771"},{"key":"ref7","first-page":"27517","article-title":"Instanceconditioned gan","volume":"34","author":"Casanova","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Magicdance: Realistic human dance video generation with motions & facial expressions transfer","author":"Chang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref10","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2669"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref14","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Black forest labs","volume-title":"Flux.1-dev","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-39964-3_62"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"issue":"4","key":"ref19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3658147","article-title":"Dresscode: Autoregressively sewing and generating garments from text guidance","volume":"43","author":"He","year":"2024","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref20","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"arXiv preprint","author":"Hu","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1408"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref25","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref27","article-title":"Anyfit: Controllable virtual tryon for any combination of attire across any scenario","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Intriguing properties of text-guided diffusion models","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","volume-title":"Deepspeed","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612137"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref32","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref35","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Podell","year":"2023"},{"key":"ref36","article-title":"Unicontrol: A unified diffusion model for controllable visual generation in the wild","author":"Qin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00605"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","article-title":"Text-guided synthesis of artistic images with retrieval-augmented diffusion models","volume-title":"arXiv preprint","author":"Rombach","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2323"},{"key":"ref42","article-title":"Retrieval-augmented score distillation for text-to-3d generation","author":"Seo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Igr: Improving diffusion model for garment restoration from person image","author":"Shen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Knndiffusion: Image generation via large-scale retrieval","author":"Sheynin","year":"2022","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Denoising diffusion implicit models","author":"Song","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Demystifying mmd gans","volume-title":"International Conference for Learning Representations","author":"Sutherland","year":"2018"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_15"},{"issue":"11","key":"ref48","article-title":"Visualizing data using t -sne","volume":"9","author":"Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref49","article-title":"Tryoffdiff: Virtual-try-off via high-fidelity garment reconstruction using diffusion models","author":"Velioglu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref51","article-title":"Tryoffanyone: Tiled cloth generation from a dressed person","author":"Xarchakos","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref55","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Geneface++: Generalized and stable realtime audio-driven 3d talking face generation","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-04928-1"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_9"},{"key":"ref63","article-title":"Controllable text-to-image generation with gpt4","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548230"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02116"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02458"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0491"}],"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\/11443574.pdf?arnumber=11443574","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:45:32Z","timestamp":1777610732000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443574\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01624","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}