[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-237948-105":3,"detail-sidebar-cat-1-en-105":81,"doc-detail-237948-en":127},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","garmatnet-a-learning-based-method-for-predicting-3d-garment-mesh-with-parameterized-materials","GarMatNet - A Learning-based Method for Predicting 3D Garment Mesh with Parameterized Materials","","GarMatNet addresses limitations in prior learning-based garment mesh generation by modeling variations in material types using parameterized material parameters under static poses. It predicts garment deformation driven by human pose and garment materials while retaining detailed wrinkle structure. The method combines a generally-fitting network for smoothed meshes and a locally-detailed network that refines wrinkles. Material effects are controlled through linear interpolation in a parameterized material space based on a mass-spring model.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/template/","Template",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/template/presentations/","Presentations",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/template/garmatnet-a-learning-based-method-for-predicting-3d-garment-mesh-with-parameterized-materials/237948/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/garmatnet-a-learning-based-method-for-predicting-3d-garment-mesh-with-parameterized-materials/237948.png","ImageObject",442,249,{"name":42,"@type":43},"Olivia Brown","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-30","2026-09-11",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",8,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does GarMatNet focus on in garment mesh generation?","Question",{"text":63,"@type":64},"GarMatNet targets how garment deformation varies with different material types using parameterized material parameters under static poses, while keeping detailed wrinkles during prediction.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How is GarMatNet structured to produce garment meshes?",{"text":68,"@type":64},"GarMatNet uses two components: a generally-fitting network to predict a smoothed garment mesh, and a locally-detailed network to add detailed wrinkles based on the smoothed result.",{"name":70,"@type":61,"acceptedAnswer":71},"How does GarMatNet represent and control material effects?",{"text":72,"@type":64},"It employs a parameterized material space based on the mass-spring model and uses linear interpolation among material factors to control deformation.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},237948,1791737859,{"code":4,"msg":82,"data":83},"success",[84,88,93,98,103,108,113,118,123],{"id":85,"doc_module":22,"doc_module_name":25,"category_name":29,"show_sort_weight":86,"slug":87},11,90,"presentations",{"id":89,"doc_module":22,"doc_module_name":25,"category_name":90,"show_sort_weight":91,"slug":92},12,"Resumes",80,"resumes",{"id":94,"doc_module":22,"doc_module_name":25,"category_name":95,"show_sort_weight":96,"slug":97},14,"Invoices",70,"invoices",{"id":99,"doc_module":22,"doc_module_name":25,"category_name":100,"show_sort_weight":101,"slug":102},15,"Posters",60,"posters",{"id":104,"doc_module":22,"doc_module_name":25,"category_name":105,"show_sort_weight":106,"slug":107},16,"Social Media",50,"social-media",{"id":109,"doc_module":22,"doc_module_name":25,"category_name":110,"show_sort_weight":111,"slug":112},17,"Forms",40,"forms",{"id":114,"doc_module":22,"doc_module_name":25,"category_name":115,"show_sort_weight":116,"slug":117},18,"Letters",30,"letters",{"id":119,"doc_module":22,"doc_module_name":25,"category_name":120,"show_sort_weight":121,"slug":122},21,"Paper Templates",5,"papers-templates",{"id":124,"doc_module":22,"doc_module_name":25,"category_name":125,"show_sort_weight":4,"slug":126},158,"General","general-158",{"code":4,"msg":82,"data":128},{"doc_id":79,"user_id":129,"nickname":42,"user_avatar":130,"doc_module":22,"category_id":85,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":131,"file_id":132,"file_url":133,"file_type":134,"file_size":135,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":136,"language":137,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":138,"faqs":139,"seo_title":140,"seo_description":12,"update_tm":141,"read_time":33},16904993612988,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","GarMatNet: A Learning-based Method for Predicting 3D Garment Mesh with Parameterized Materials  \nZhen Luo  \n[luo.utokyo@gmail.com](luo.utokyo@gmail.com)[ ](luo.utokyo@gmail.com)The University of Tokyo Meguro, Tokyo, Japan  \nTianxing Li  \n[li-tianxing@hotmail.com](li-tianxing@hotmail.com)[ ](li-tianxing@hotmail.com)The University of Tokyo Meguro, Tokyo, Japan  \nTakashi Kanai  \n[kanait@acm.org](kanait@acm.org)[ ](kanait@acm.org)The University of Tokyo Meguro, Tokyo, Japan  \nGenerally-fitting Network Locally-detailed Network  \nMaterial 1 Material 1  \nFigure 1: Whole pipeline of GarMatNet.  \nABSTRACT  \nRecent progress in learning-based methods of garment mesh generation is resulting in increased efficiency and maintenance of reality during the generation process. However, none of the previous works so far have focused on variations in material types based on a parameterized material parameter under static poses. In this work, we propose a learning-based method, GarMatNet, for predicting garment deformation based on the functions of human poses and garment materials while maintaining detailed garment wrinkles. GarMatNet consists of two components: a generally-fitting network for predicting smoothed garment mesh and a locally-detailed network for adding detailed wrinkles based on smoothed garment mesh. We hypothesize that material properties play an essential role in the deformation of garments. Since the influences of material type are relatively smaller than pose or body shape, we employ linear interpolation among different factors to control deformation. More specifically, we apply a parameterized material space based on the mass-spring model to express the difference between materials  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nMIG’21, November 10–12, 2021, Virtual Event, Switzerland  \n© 2021 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 978-1-4503-9131-3/21/11. . . $15.00  \n[https://doi.org/10.1145/3487983.3488294](https://doi.org/10.1145/3487983.3488294)  \nand construct a suitable network structure with weight adjustment between material properties and poses. The experimental results demonstrate that GarMatNet is comparable to the physically-based simulation (PBS) prediction and offers advantages regarding generalization ability, model size, and training time over the baseline model.  \nCCS CONCEPTS  \n• Computing methodologies → Animation; Artificial intelligence.  \nKEYWORDS  \nNeural networks, garment deformation, animation  \nACM Reference Format:  \nZhen Luo, Tianxing Li, and Takashi Kanai. 2021. GarMatNet: A Learningbased Method for Predicting 3D Garment Mesh with Parameterized Materials. In Motion, Interaction and Games (MIG ’21), November 10–12, 2021, Virtual Event, Switzerland. ACM, New York, NY, USA, 10 pages. [https:](https:)//[doi.org/10.1145/3487983.3488294](doi.org/10.1145/3487983.3488294)  \n1 INTRODUCTION  \nMesh generation of clothed humans benefits a lot of applications such as virtual try-on, game, digital fashion design, and 3D content production. With the increasing need for interactive applications, demands for real-time 3D visualization are increasingly growing. However, the simulation of garments on the human body is still  \nchallenging in computer graphics research because of the complexity of garment wrinkles in various poses, body shapes, garment styles, and garment materia","cbCaifNjt1NArCnT","https://ap.wps.com/l/cbCaifNjt1NArCnT","pdf",6285617,10,"English","# Abstract\n# Introduction\n## Applications of 3D Garment Mesh Generation\n## Physically-Based Simulation (PBS) Approaches\n## Learning-Based Real-Time Methods\n## GarMatNet and Parameterized Materials","[{\"question\":\"What problem does GarMatNet focus on in garment mesh generation?\",\"answer\":\"GarMatNet targets how garment deformation varies with different material types using parameterized material parameters under static poses, while keeping detailed wrinkles during prediction.\"},{\"question\":\"How is GarMatNet structured to produce garment meshes?\",\"answer\":\"GarMatNet uses two components: a generally-fitting network to predict a smoothed garment mesh, and a locally-detailed network to add detailed wrinkles based on the smoothed result.\"},{\"question\":\"How does GarMatNet represent and control material effects?\",\"answer\":\"It employs a parameterized material space based on the mass-spring model and uses linear interpolation among material factors to control deformation.\"}]","GarMatNet - A Learning-based Method for Predicting 3D Garment Mesh with Parameterized Materials | PDF",1789128329]