{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:18:34Z","timestamp":1778285914292,"version":"3.51.4"},"reference-count":49,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T00:00:00Z","timestamp":1747872000000},"content-version":"vor","delay-in-days":141,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Image Processing"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>To address the issue of image distortion caused by substantial structural discrepancies between original garment images and reference images in the application of image transfer technology for fashion design, this study proposes a region\u2010aware fashion design method based on a probabilistic diffusion model. During the image feature extraction and output stage, the method integrates vision transformer (ViT) with a mask\u2010guided mechanism, enabling the Diffusion model to precisely focus on the transferable regions of the original and reference images, thereby preserving the structural integrity and semantic consistency of the source images effectively. In the image colour and pattern style transfer stage, this study introduces an asymmetric gradient guidance (AGG) strategy to optimise the reverse sampling process of the diffusion model, substantially improving the quality and visual fidelity of the generated images. Experimental results indicate that this method achieves a Fr\u00e9chet inception distance (FID) score of 103.4, surpassing existing fashion synthesis models. This facilitates the generation of more stable and realistic images for garment design tasks.<\/jats:p>","DOI":"10.1049\/ipr2.70103","type":"journal-article","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T23:55:09Z","timestamp":1747958109000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Study on Region\u2010Aware Fashion Design Based on Probabilistic Diffusion Model"],"prefix":"10.1049","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9000-1637","authenticated-orcid":false,"given":"Jie","family":"Sun","sequence":"first","affiliation":[{"name":"School of Fashion Design &amp; Engineering Zhejiang Sci\u2010Tech University  Hangzhou China"},{"name":"School of Design and Art Communication University of Zhejiang  Hangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kejun","family":"Cen","sequence":"additional","affiliation":[{"name":"School of Fashion Design &amp; Engineering Zhejiang Sci\u2010Tech University  Hangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojun","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Fashion Design &amp; Engineering Zhejiang Sci\u2010Tech University  Hangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarah","family":"Haidar","sequence":"additional","affiliation":[{"name":"School of Fashion Design &amp; Engineering Zhejiang Sci\u2010Tech University  Hangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengyuan","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Fashion Design &amp; Engineering Zhejiang Sci\u2010Tech University  Hangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"265","published-online":{"date-parts":[[2025,5,22]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/pr10122744"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3057892"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1177\/00405175211034245"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.3390\/app121910042"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3306235"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3567596"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3290149"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3318297"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.3390\/app12157785"},{"key":"e_1_2_10_11_1","doi-asserted-by":"crossref","unstructured":"A.Voynov K.Aberman andD.Cohen\u2010Or \u201cSketch\u2010Guided Text\u2010to\u2010Image Diffusion Models \u201d inACM SIGGRAPH'23: Special Interest Group on Computer Graphics and Interactive Techniques ConferenceLos Angeles CA USA August 6\u201310 2023.","DOI":"10.1145\/3588432.3591560"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3224190"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1049\/cvi2.12295"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.092"},{"key":"e_1_2_10_15_1","doi-asserted-by":"crossref","unstructured":"JiangandY.Fu \u201cFashion Style Generator \u201d inProceedings of the International Joint Conference on Artificial IntelligenceMelbourne Australia August 19\u201325 2017.","DOI":"10.24963\/ijcai.2017\/520"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3255831"},{"key":"e_1_2_10_17_1","first-page":"262","article-title":"Texture Synthesis Using Convolutional Neural Networks","volume":"70","author":"Gatys L.","year":"2015","journal-title":"NeurIPS"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3353530"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3372940"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3482560"},{"key":"e_1_2_10_21_1","unstructured":"P.Date A.Ganesan andT.Oates \u201cFashioning With Networks: Neural Style Transfer to Design Clothes 2017 \u201d arXiv preprint arXiv:1707.09899 (2017)."},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3146010"},{"key":"e_1_2_10_23_1","doi-asserted-by":"crossref","unstructured":"O.Sbai M.Elhoseiny A.Bordes Y.LeCun andC.Couprie \u201cDeSIGN: Design Inspiration From Generative Networks \u201d arXiv preprint arXiv:1804.00921 (2018).","DOI":"10.1007\/978-3-030-11015-4_5"},{"key":"e_1_2_10_24_1","unstructured":"I. J.Goodfellow P. A.Jean M.Mirza et\u00a0al. \u201cConditional Generative Adversarial Nets \u201d inProceedings of the 27th International Conference on Neural Information Processing SystemsMontreal Canada December 8\u201313 2014."},{"key":"e_1_2_10_25_1","unstructured":"X.Su J.Song C.Meng andS.Ermon \u201cDual Diffusion Implicit Bridges for Image\u2010to\u2010Image Translation \u201d arXiv preprint arXiv:2203.08382 (2022)."},{"key":"e_1_2_10_26_1","unstructured":"P.DhariwalandA.Nichol \u201cDiffusion Models Beat GANs on Image Synthesis \u201d arXiv preprint arXiv:2105.05233 (2021)."},{"key":"e_1_2_10_27_1","doi-asserted-by":"crossref","unstructured":"R.Rombach A.Blattmann D.Lorenz P.Esser andB.Ommer \u201cHigh\u2010Resolution Image Synthesis With Latent Diffusion Models \u201d arXiv preprint arXiv:2112.10752 (2022).","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acca5c"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1049\/cvi2.12215"},{"key":"e_1_2_10_30_1","doi-asserted-by":"crossref","unstructured":"J.Karras A.Holynski T.Wang andI.Kemelmacher\u2010Shlizerman \u201cDreamPose: Fashion Image\u2010to\u2010Video Synthesis via Stable Diffusion \u201d in Proceedings of theIEEE\/CVF International Conference on Computer Vision (ICCV)Paris France October 4\u20136 2023.","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"e_1_2_10_31_1","unstructured":"Y.Song J. S.Dickstein D. P.Kingma et\u00a0al. \u201cScore\u2010based generative modeling through stochastic differential equations \u201d arXiv preprint arXiv:2011.13456 (2020)."},{"key":"e_1_2_10_32_1","unstructured":"J.Ho A.Jain andP.Abbeel \u201cDenoising Diffusion Probabilistic Models \u201d inProceedings of the 34th Conference on Neural Information Processing SystemsVancouver Canada December 6\u201312 2020."},{"key":"e_1_2_10_33_1","unstructured":"A.NicholandP.Dhariwal \u201cImproved Denoising Diffusion Probabilistic Models \u201d inProceedings of the 38th International Conference on Machine Learning(Online) July 18\u201324 2021."},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.3390\/fi15120374"},{"key":"e_1_2_10_35_1","unstructured":"C.Mou X.Wang J.Song Y.Shan andJ.Zhang \u201cDragonDiffusion: Enabling Drag\u2010Style Manipulation on Diffusion Models \u201d arXiv preprint arXiv:2307.02421 (2023)."},{"key":"e_1_2_10_36_1","doi-asserted-by":"crossref","unstructured":"J.Zhang C.Herrmann J.Hur et\u00a0al. \u201cA tale of two features: Stable Diffusion Complements Dino for Zero\u2010Shot Semantic Correspondence \u201d arXiv preprint arXiv:2305.15347 (2023).","DOI":"10.52202\/075280-1973"},{"key":"e_1_2_10_37_1","doi-asserted-by":"crossref","unstructured":"M.Caron H.Touvron I.Ishan Misra et\u00a0al. \u201cEmerging Properties in Self\u2010Supervised Vision Transformers \u201d inProceedings of the IEEE\/CVF International Conference on Computer VisionMontreal QC Canada October 10\u201317 2021.","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_2_10_38_1","unstructured":"G.KwonandJ. C.Ye \u201cDiffusion\u2010based Image Translation Using Disentangled Style and Content Representation \u201d inProceedings of the International Conference on Learning Representations (arXiv arXiv:2209.15264 2023)."},{"key":"e_1_2_10_39_1","doi-asserted-by":"crossref","unstructured":"J.Choi S.Kim Y.Jeong Y.Gwon andS.Yoon \u201cILVR: Conditioning Method for Denoising Diffusion Probabilistic Models \u201d inProceedings of the IEEE\/CVF International Conference on Computer Vision(Montreal QC Canada October10\u201317 2021).","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"e_1_2_10_40_1","unstructured":"Y. S.Chenlin Meng J.Song J.Wu J.\u2010Y.Zhu andS.Ermon \u201cSDEdit: Guided Image Synthesis and Editing With Stochastic Differential Equations \u201d arXiv:2108.01073 (2023)."},{"key":"e_1_2_10_41_1","doi-asserted-by":"crossref","unstructured":"X.Liu D. H.Park S.Azadi et\u00a0al. \u201cMore Control for Free! Image Synthesis With Semantic Diffusion Guidance \u201d inProceedings of the IEEE\/CVF Winter Conference on Applications of Computer VisionWaikoloa HI USA January 2\u20137 .2023.","DOI":"10.1109\/WACV56688.2023.00037"},{"key":"e_1_2_10_42_1","doi-asserted-by":"crossref","unstructured":"J.Deng W.Dong R.Socher L. J.Li K.Li andF. F.Li \u201cImageNet: A Large\u2010Scale Hierarchical Image Database \u201d inProceedings of the IEEE Conference on Computer Vision and Pattern RecognitionMiami FL USA June 20\u201325 2009.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_10_43_1","doi-asserted-by":"crossref","unstructured":"H.Chung B.Sim D.Ryu andJ. C.Ye \u201cImproving Diffusion Models for Inverse Problems Using Manifold Constraints \u201d arXiv preprint arXiv:2206.00941 (2022).","DOI":"10.52202\/068431-1862"},{"key":"e_1_2_10_44_1","doi-asserted-by":"crossref","unstructured":"R.Gal O.Patashnik H.Maron G.Chechik andD.Cohen\u2010Or \u201cStyleGAN\u2010NADA: Clip\u2010Guided Domain Adaptation of Image Generators \u201d arXiv arXiv:2108.00946 (2021).","DOI":"10.1145\/3528223.3530164"},{"key":"e_1_2_10_45_1","unstructured":"H.Chung S.Lee andJ. C.Ye \u201cFast Diffusion Sampler for Inverse Problems by Geometric Decomposition \u201d arXiv preprint arXiv:2303.05754v3 (2023)."},{"key":"e_1_2_10_46_1","doi-asserted-by":"crossref","unstructured":"A.Bansal H. M.Chu A.Schwarzschild et\u00a0al. \u201cUniversal Guidance for Diffusion Models \u201d arXivpreprint arXiv:2302.07121 (2023).","DOI":"10.1109\/CVPRW59228.2023.00091"},{"key":"e_1_2_10_47_1","unstructured":"G.Couairon J.Verbeek H.Schwenk andM.Cord \u201cDiffEdit: Diffusion\u2010Based Semantic Image Editing With Mask Guidance \u201d arXiv preprint arXiv:abs\/2210.11427."},{"key":"e_1_2_10_48_1","first-page":"864","article-title":"Noise2Score: Tweedie's Approach to Self\u2010Supervised Image Denoising Without Clean Images","volume":"34","author":"Kim K.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_49_1","unstructured":"V.Khrulkov G.Ryzhakov A.Chertkov andI.Oseledets \u201cUnderstanding DDPM Latent Codes Through Optimal Transport \u201d inProceedings of the International Conference on Learning Representations. (arXiv arXiv:2202.07477 2023)."},{"key":"e_1_2_10_50_1","doi-asserted-by":"crossref","unstructured":"N.Tumanyan O.Bar\u2010Tal S.Bagon andT.Dekel \u201cSplicing ViT Features for Semantic Appearance Transfer \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern RecognitionNew Orleans LA USA June 18\u201324 2022.","DOI":"10.1109\/CVPR52688.2022.01048"}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70103","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/ipr2.70103","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70103","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:04:22Z","timestamp":1778285062000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.70103"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1049\/ipr2.70103"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.70103","archive":["Portico"],"relation":{},"ISSN":["1751-9659","1751-9667"],"issn-type":[{"value":"1751-9659","type":"print"},{"value":"1751-9667","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2024-12-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70103"}}