[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-272294-105":59,"doc-detail-272294-en":122},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":115,"head_meta":117,"extra_data":119,"updated_unix":121},105,"en","scalable-and-realistic-virtual-try-on-application-for-foundation-makeup-with-kubelka-munk-theory","Scalable and Realistic Virtual Try-on Application for Foundation Makeup with Kubelka-Munk Theory","","Augmented reality is transforming the beauty industry by enabling virtual try-on (VTO) on mobile devices, letting users preview many products without physically applying them. A core technical difficulty is producing accurate foundation-to-skin tone color blending while keeping the approach scalable across diverse product catalogs. This work introduces a method that approximates Kubelka-Munk (KM) theory for faster synthesis and maintains realism. It further builds an end-to-end foundation makeup VTO framework using only product information from e-commerce sites, validated on real makeup images outperforming prior techniques.",{"@graph":69,"@context":114},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":30,"@type":76,"position":81},"https://docshare.wps.com/document/technology/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/scalable-and-realistic-virtual-try-on-application-for-foundation-makeup-with-kubelka-munk-theory/272294/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/scalable-and-realistic-virtual-try-on-application-for-foundation-makeup-with-kubelka-munk-theory/272294.png","ImageObject",300,407,{"name":92,"@type":93},"Elsa","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-07","2026-09-15",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108],{"name":109,"@type":110,"acceptedAnswer":111},"What information does the end-to-end framework rely on to generate realistic results?","Question",{"text":112,"@type":113},"The framework depends only on product information available on e-commerce sites. It does not require extra specialized cosmetic optical measurements in the described pipeline.","Answer","https://schema.org",{"og:url":83,"og:type":116,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":118,"canonical":83},"index,follow",{"doc_id":120,"site_id":62},272294,1790471317,{"code":4,"msg":5,"data":123},{"doc_id":120,"user_id":124,"nickname":92,"user_avatar":125,"doc_module":4,"category_id":29,"category_name":30,"doc_title":65,"doc_description":67,"doc_content":126,"file_id":127,"file_url":128,"file_type":129,"file_size":130,"view_count":44,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":131,"language":132,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":133,"faqs":134,"seo_title":135,"seo_description":67,"update_tm":136,"read_time":137},137455077381,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","Scalable and Realistic Virtual Try-on Application for Foundation Makeup with Kubelka-Munk Theory  \nHui Pang Sunil Hadap Violetta Shevchenko * Rahul Suresh *  \nAmin Banitalebi-Dehkordi  \nAmazon  \narXiv :2507 .07333v 1 [ cs .CV] 9 Jul 2025  \nAbstract  \nAugmented reality is revolutionizing beauty industry with virtual try-on (VTO) applications, which empowers users to try a wide variety of products using their phones without the hassle of physically putting on real products. A critical technical challenge in foundation VTO applications is the accurate synthesis of foundation-skin tone color blending while maintaining the scalability of the method across diverse product ranges. In this work, we propose a novel method to approximate well-established Kubelka-Munk (KM) theory for faster image synthesis while preserving foundation-skin tone color blending realism. Additionally, we build a scalable end-to-end framework for realistic foundation makeup VTO solely depending on the product information available one-commerce sites. We validate our method using real-world makeup images, demonstrating that our framework outperforms other techniques.  \n1. Introduction  \nVirtual try-on (VTO) applications have transformed the way users shop for beauty products online. Prior to the advent of VTO, shoppers were limited to relying on static product images and reviews, often resulting in uncertainty about color compatibility and overall look. VTO applications provide a realistic simulation of how the product would appear on face, enabling informed buying decisions.  \nColor accuracy is crucial to foundation virtual try-on applications. Although recent makeup transfer models, e.g. BeautyREC [34], EleGANT [35] and SSAT [30] demonstrate proficiency in color and pattern transfer, they fail to account for the critical interaction between underlying skin tones and foundation products (See Fig. 8) . This limitation significantly impacts their reliability as decision-making tools for consumer purchases. To extract accurate skin tones from images, there have been multiple works trying to dis-  \n*Work done at Amazon  \nFigure 1 . End-to-end framework of foundation virtual try-on application. First, we create a face semantic segmentation mask and decompose face image into albedo, shading and specular highlight layers. Then we estimate the reflectance of albedo layer as well asthe reflectance of foundation product based on sRGB values. Then we utilize our approximation for Kubelka-Munk model to blend foundation shade with albedo. Finally, we reconstruct the image with blended albedo, shading and specular highlight.  \nentangle skin albedo color from shading and highlight inan image [7, 19, 27] . A significant challenge persists in the accurate representation of various skin tones. Beside accurate skin tone extraction, VTO applications must accurately show the color of foundation applied on skin. While alpha blending[33] has been widely adopted for its computational efficiency and implementation simplicity, it fails to capture the complex optical interactions of real-world foundation shade blending with skin tone. At the same time, the acquisition of optical properties for cosmetic products are expensive, as the measurement process requires specialized equipment and extensive laboratory analysis [1, 6, 8, 13, 22, 32] . There-  \nfore, another challenge in constructing VTO applications lie in striking a balance between delivering highly realistic results and ensuring the technology is scalable to accommodate diverse beauty products and skin tones.  \nIn this paper, we propose an end-to-end framework that achieves realistic rendering of foundation products relying only on the product information available on e-commerce sites. We first trained a face semantic segmentation model to locate the region for the product application, and developed a simple and fast intrinsic image decomposition method to separate the face skin tone from the shading and specular highlight effec","cbCaioFxJas8rkZM","https://ap.wps.com/l/cbCaioFxJas8rkZM","pdf",18318888,11,"English","# 1. Introduction\n# 2. Related Work","[{\"question\":\"What information does the end-to-end framework rely on to generate realistic results?\",\"answer\":\"The framework depends only on product information available on e-commerce sites. It does not require extra specialized cosmetic optical measurements in the described pipeline.\"}]","Scalable and Realistic Virtual Try-on Application for Foundation Makeup with Kubelka-Munk Theory | PDF",1789464188,28]