[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84421-en":3,"doc-seo-84421-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},84421,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Training-Free Identity-Preserving Image Editing for Fashion Pose Alignment and Normalization","Diffusion models enable real-world image editing, but non-rigid object changes—such as pose adjustment or conditioning—remain difficult, especially when the edited result must keep the object’s unique identity and brand-consistent appearance. Existing approaches often require specialized training data, which may be unavailable in practical settings and is costly to produce. FashionRepose is introduced as a novel training-free pipeline for the fashion industry, using pretrained off-the-shelf models for long-sleeve garment pose modification while preserving identity. A zero-shot strategy supports near real-time edits, and FashionRepose is deployed by OVS on 30,000+ garments.","arXiv :2501 . 13692v2 [ cs .CV] 12 Jul 2026  \nTraining-Free, Identity-Preserving Image Editing for Fashion Pose Alignment and Normalization  \nPotito Aghilara,b,∗, Vito Walter Anellia , Michelantonio Triziob , Eugenio Di  \nSciascioa , Tommaso Di Noiaa  \na Polytechnic University of Bari, Via Edoardo Orabona, 4, Bari, 70125, Apulia, Italy b Wideverse, Via Edoardo Orabona, 4, Bari, 70125, Apulia, Italy  \nAbstract  \nDiffusion models have recently unlocked new possibilities in editing images of real-world objects. Yet, transforming objects in non-rigid ways, such as modifying poses or applying image-based conditioning, continues to present significant challenges. Retaining the unique identity of objects during these edits is a complex task, and current techniques often fall short of delivering the precision needed for industrial settings, where consistency is nonnegotiable. Additionally, adapting diffusion models demands custom training data, which is often unavailable in real-world scenarios. To address these gaps, we present FashionRepose, a novel, training-free pipeline designed to handle non-rigid pose adjustments specifically for the fashion industry. This approach combines pretrained off-the-shelf models to modify the poses of long-sleeve garments while safeguarding their identity and branding characteristics. By adopting a zero-shot methodology, FashionRepose enables near real-time edits, entirely eliminating the requirement for specialized training data. FashionRepose has been deployed for a global fashion firm, OVS, handling more than 30,000 long-sleeve garments.  \nKeywords: Diffusion models, Computer vision, Software engineering, Large language models  \n∗ Corresponding author  \nEmail addresses: potito.aghilar@poliba.it, [potito.aghilar@wideverse.com](potito.aghilar@wideverse.com)  \n(Potito Aghilar), vitowalter.anelli@poliba.it (Vito Walter Anelli),  \n[michelantonio.trizio@poliba.it](michelantonio.trizio@poliba.it) , [michelantonio.trizio@wideverse.com](michelantonio.trizio@wideverse.com)  \n(Michelantonio Trizio), [eugenio.disciascio@poliba.it](eugenio.disciascio@poliba.it) (Eugenio Di Sciascio), [tommaso.dinoia@poliba.it](tommaso.dinoia@poliba.it) (Tommaso Di Noia)  \n1. Introduction  \nThe digital transformation of the fashion industry has placed a growing emphasis on image editing, which has become a cornerstone of e-commerce, marketing, and design. Fashion brands today heavily rely on the ability to modify garment poses, alter colors, and visualize new styles for diverse audiences. These capabilities streamline workflows, reduce costs, and provide enhanced customer experiences (Mohammadi and Kalhor, 2021) . However, the challenge of achieving non-rigid transformations – particularly pose adjustments or normalization (Zhao et al., 2023)– remains unresolved. This is especially critical for maintaining brand identity, which relies on consistency in visual representation. The increasing demand for personalized and engaging content has only intensified the pressure on brands to adopt efficient yet precise image editing techniques that can scale with consumer expectations.  \nTraditional graphic tools like Photoshop 1 and Illustrator 2 have been the industry standard for decades, enabling precise but highly manual editing workflows (Hume, 2016; Caruso and Postel, 2002; Altenburg, 2014; Hume, 2016) . While effective, these tools demand significant time and expertise, making scalability a persistent issue. Editors need to iterate over numerous design variants manually, a task that becomes increasingly laborious as product lines expand or marketing campaigns diversify. This bottleneck can hinder a brand’s ability to remain agile when faced with rapidly changing trends. In contrast, advancements in Artificial Intelligence (AI) and Machine Learning (ML) have introduced automated methods capable of generating photorealistic virtual samples in minutes. These innovations shorten product design cycles, enhance collaboration between desig","cbCaihCAL0itIA0M","https://ap.wps.com/l/cbCaihCAL0itIA0M","pdf",4136145,1,42,"English","en",105,"# Introduction\n## Challenges in Non-Rigid Fashion Editing\n## Limitations of Traditional and Existing AI Methods","[{\"question\":\"What problem does FashionRepose address in fashion image editing?\",\"answer\":\"FashionRepose addresses non-rigid transformations such as pose adjustment or normalization while preserving the garment’s identity and branding-consistent appearance.\"},{\"question\":\"Why is a training-free approach important for this task?\",\"answer\":\"Adapting diffusion models typically requires custom training data, which is often unavailable in real-world scenarios; FashionRepose eliminates this dependency.\"},{\"question\":\"How does FashionRepose perform pose edits without specialized training data?\",\"answer\":\"It uses a zero-shot methodology that combines pretrained off-the-shelf models to modify poses of long-sleeve garments while safeguarding their identity characteristics.\"}]",1784195529,106,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"training-free-identity-preserving-image-editing-for-fashion-pose-alignment-and-normalization","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/training-free-identity-preserving-image-editing-for-fashion-pose-alignment-and-normalization/84421/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does FashionRepose address in fashion image editing?","Question",{"text":75,"@type":76},"FashionRepose addresses non-rigid transformations such as pose adjustment or normalization while preserving the garment’s identity and branding-consistent appearance.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why is a training-free approach important for this task?",{"text":80,"@type":76},"Adapting diffusion models typically requires custom training data, which is often unavailable in real-world scenarios; FashionRepose eliminates this dependency.",{"name":82,"@type":73,"acceptedAnswer":83},"How does FashionRepose perform pose edits without specialized training data?",{"text":84,"@type":76},"It uses a zero-shot methodology that combines pretrained off-the-shelf models to modify poses of long-sleeve garments while safeguarding their identity characteristics.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]