[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-238561-105":53,"doc-detail-238561-en":126},{"code":4,"msg":5,"data":6},0,"success",[7,14,19,24,29,34,39,44,49],{"id":8,"doc_module":9,"doc_module_name":10,"category_name":11,"show_sort_weight":12,"slug":13},11,1,"Template","Presentations",90,"presentations",{"id":15,"doc_module":9,"doc_module_name":10,"category_name":16,"show_sort_weight":17,"slug":18},12,"Resumes",80,"resumes",{"id":20,"doc_module":9,"doc_module_name":10,"category_name":21,"show_sort_weight":22,"slug":23},14,"Invoices",70,"invoices",{"id":25,"doc_module":9,"doc_module_name":10,"category_name":26,"show_sort_weight":27,"slug":28},15,"Posters",60,"posters",{"id":30,"doc_module":9,"doc_module_name":10,"category_name":31,"show_sort_weight":32,"slug":33},16,"Social Media",50,"social-media",{"id":35,"doc_module":9,"doc_module_name":10,"category_name":36,"show_sort_weight":37,"slug":38},17,"Forms",40,"forms",{"id":40,"doc_module":9,"doc_module_name":10,"category_name":41,"show_sort_weight":42,"slug":43},18,"Letters",30,"letters",{"id":45,"doc_module":9,"doc_module_name":10,"category_name":46,"show_sort_weight":47,"slug":48},21,"Paper Templates",5,"papers-templates",{"id":50,"doc_module":9,"doc_module_name":10,"category_name":51,"show_sort_weight":4,"slug":52},158,"General","general-158",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":119,"head_meta":121,"extra_data":123,"updated_unix":125},105,"en","cloth2tex-customized-cloth-texture-generation-pipeline-for-3d-virtual-try-on-abstract","Cloth2Tex - Customized Cloth Texture Generation Pipeline for 3D Virtual Try-On - Abstract","","Fabricating and designing 3D garments is increasingly demanding for realistic dressed-person synthesis across applications such as 3D virtual try-on, converting 2D clothing references into 3D apparel, and cloth animation. A simple pipeline is needed to produce high-quality texture maps from limited inputs, while avoiding the tedious manual selection required by warping-based methods. Cloth2Tex introduces a self-supervised texture generation pipeline that yields consistent layouts and structures and supports high-fidelity texture inpainting by integrating with a latent diffusion model.",{"@graph":63,"@context":118},[64,80,101],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,71,74,77],{"item":68,"name":69,"@type":70,"position":9},"https://docshare.wps.com","Home","ListItem",{"item":72,"name":10,"@type":70,"position":73},"https://docshare.wps.com/template/",2,{"item":75,"name":51,"@type":70,"position":76},"https://docshare.wps.com/template/general/",3,{"item":78,"name":59,"@type":70,"position":79},"https://docshare.wps.com/template/cloth2tex-customized-cloth-texture-generation-pipeline-for-3d-virtual-try-on-abstract/238561/",4,{"url":78,"name":59,"@type":81,"image":82,"author":87,"headline":59,"publisher":90,"fileFormat":93,"inLanguage":57,"description":61,"dateModified":94,"datePublished":95,"encodingFormat":93,"isAccessibleForFree":96,"interactionStatistic":97},"DigitalDocument",{"url":83,"@type":84,"width":85,"height":86},"https://docshare.wps.com/thumbnails/cloth2tex-customized-cloth-texture-generation-pipeline-for-3d-virtual-try-on-abstract/238561.png","ImageObject",442,249,{"name":88,"@type":89},"Taylor Morgan","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/pdf","2026-09-21","2026-09-11",true,{"@type":98,"interactionType":99,"userInteractionCount":9},"InteractionCounter",{"@type":100},"ViewAction",{"@type":102,"mainEntity":103},"FAQPage",[104,110,114],{"name":105,"@type":106,"acceptedAnswer":107},"What problem does Cloth2Tex address in 3D virtual try-on?","Question",{"text":108,"@type":109},"It converts 2D clothing catalog images into high-quality 3D textured meshes, overcoming incompatibility with 3D pipelines and improving texture completeness across diverse garment types.","Answer",{"name":111,"@type":106,"acceptedAnswer":112},"How does Cloth2Tex improve over Thin-Plate-Spline (TPS) warping approaches?",{"text":113,"@type":109},"Instead of TPS, it uses neural mesh rendering to establish dense correspondences, producing higher-quality initial texture maps and reducing issues caused by self-occlusions.",{"name":115,"@type":106,"acceptedAnswer":116},"How does Cloth2Tex perform texture refinement and inpainting?",{"text":117,"@type":109},"It leverages a latent diffusion model and combines Cloth2Tex with ControlNet to simulate refined textures, then trains refinement using pairs of complete and defective texture maps.","https://schema.org",{"og:url":78,"og:type":120,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":122,"canonical":78},"index,follow",{"doc_id":124,"site_id":56},238561,1790016101,{"code":4,"msg":5,"data":127},{"doc_id":124,"user_id":128,"nickname":88,"user_avatar":129,"doc_module":9,"category_id":50,"category_name":51,"doc_title":59,"doc_description":61,"doc_content":130,"file_id":131,"file_url":132,"file_type":133,"file_size":134,"view_count":9,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":25,"language":135,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":136,"faqs":137,"seo_title":138,"seo_description":61,"update_tm":139,"read_time":47},1099523885336,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Cloth2Tex: A Customized Cloth Texture Generation Pipeline for 3D Virtual  \nTry-On  \nDaiheng Gao 1∗ Xu Chen2 ,3∗ Xindi Zhang 1 Qi Wang 1  \nKe Sun 1 Bang Zhang 1 Liefeng Bo 1 Qixing Huang4  \n1Alibaba XR Lab 2ETH Zurich, Department of Computer Science  \n3Max Planck Institute for Intelligent Systems 4The University of Texas at Austin  \nFigure 1 . We propose Cloth2Tex, a novel pipeline for converting 2D images of clothing to high-quality 3D textured meshes that can bedraped onto 3D humans. In contrast to previous methods, Cloth2Tex supports a variety of clothing types. Results of 3D textured meshes produced by our method as well as the corresponding input images are shown above.  \nAbstract  \nFabricating and designing 3D garments has become extremely demanding with the increasing need for synthesizing realistic dressed persons for a variety of applications, e.g. 3D virtual try-on, digitalization of 2D clothes into 3D apparel, and cloth animation. It thus necessitates a simple and straightforward pipeline to obtain high-quality texture from simple input, such as 2D reference images. Since traditional warping-based texture generation methods require a significant number of control points to be manually selected for each type of garment, which can be a time-consuming and tedious process. We propose a novel method, called Cloth2Tex, which eliminates the human burden in this process. Cloth2Tex is a self-supervised method that generates texture maps with reasonable layout and structural consistency. Another key feature of Cloth2Tex is that it can be used to support high-fidelity texture inpainting. This is done by combining Cloth2Tex with a prevailing latent diffusion model. We evaluate our approach both qualitatively and  \nquantitatively and demonstrate that Cloth2Tex can generate high-quality texture maps and achieve the best visual effects in comparison to other methods. Project page: xxx  \n1. Introduction  \nThe advancement of AR/VR and 3D graphics has opened up new possibilities for the fashion e-commerce industry. Customers can now virtually try on clothes on their avatarsin 3D, which can help them make more informed purchase decisions. However, most clothing assets are currently presented in 2D catalog images, which are incompatible with 3D graphics pipelines. Thus it is critical to produce 3D clothing assets automatically from these existing 2D images, aiming at making 3D virtual try-on accessible to everyone.  \nTowards this goal, the research community has been developing algorithms [19, 20, 37] that can transfer 2D images into 3D textures of clothing mesh models. The key  \nFigure 2 . Problem of warping-based texture generation algorithm: partially filled UV texture maps with large missing holes as highlighted in yellow.  \nto producing 3D textures from 2D images is to determine the correspondences between the catalog images and the UV textures. Conventionally, this is achieved via the ThinPlate-Spline (TPS) method [3], which approximates the dense correspondences from a small set of corresponding key points. In industrial applications, these key points are annotated manually and densely for each clothing instance to achieve good quality. With deep learning models, automatic key point detectors [19, 35] have been proposed to detect key points automatically for clothing. However, as seen in Fig. 2, the inherent self-occlusions (e.g. sleeves occluded by the main fabric) of TPS warping-based approaches are intractable, leading to erroneous and incomplete texture maps. Several works have attempted to use generative models to refine texture maps. However, such a refinement strategy has demonstrated success only in a small set of clothing types, i.e. T-shirts, pants, and shorts. This is because TPS cannot produce satisfactory initial texture maps on all clothing types, and a large training dataset covering high-quality texture maps of diverse clothing types is missing. Pix2Surf [20], a SMPL [18]-based virtual tryon algorithm, has automat","cbCaiapWuvrAEDP8","https://ap.wps.com/l/cbCaiapWuvrAEDP8","pdf",50379948,"English","# Introduction\n## Motivation and problem setup\n## Background on warping-based methods\n## Proposed contributions","[{\"question\":\"What problem does Cloth2Tex address in 3D virtual try-on?\",\"answer\":\"It converts 2D clothing catalog images into high-quality 3D textured meshes, overcoming incompatibility with 3D pipelines and improving texture completeness across diverse garment types.\"},{\"question\":\"How does Cloth2Tex improve over Thin-Plate-Spline (TPS) warping approaches?\",\"answer\":\"Instead of TPS, it uses neural mesh rendering to establish dense correspondences, producing higher-quality initial texture maps and reducing issues caused by self-occlusions.\"},{\"question\":\"How does Cloth2Tex perform texture refinement and inpainting?\",\"answer\":\"It leverages a latent diffusion model and combines Cloth2Tex with ControlNet to simulate refined textures, then trains refinement using pairs of complete and defective texture maps.\"}]","Cloth2Tex - Customized Cloth Texture Generation Pipeline for 3D Virtual Try-On - Abstract | PDF",1789137907]