[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85173-en":3,"doc-seo-85173-105":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},85173,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","LFD: Enabling Real-World Lensless Face Recognition with a Large-Scale Dataset","Face recognition supports everyday biometrics and high-stakes security, yet conventional lens-based cameras face constraints in size, cost, and privacy. Lensless cameras use thin optical encoders and reconstruction algorithms, but reconstructed results contain modality-specific artifacts and methods generalize poorly to real-world conditions. Existing datasets also miss lensless artifacts. Lensless Face Dataset (LFD) provides 21,080 lensless raw measurements, reconstructions, and standard images under varied lighting, angles, and distances. It includes outdoor in-the-wild captures, hardware diversity across three devices, and evaluation showing shared features and artifacts for robust lensless recognition.","arXiv :2607 . 10094v1 [ cs .CV] 11 Jul 2026  \nLFD: Enabling Real-World Lensless Face Recognition with a Large-Scale Dataset  \nJunho Kim*, Salman S. Khan*, Sara Wan, Tomi Kuye, Ashok Veeraraghavan  \nAbstract—Face recognition is a ubiquitously used computer vision task that has a wide range of applications ranging from everyday smartphone biometrics to high-stakes security systems. Most face recognition systems rely on traditional cameras, which often suffer from limitations such as bulky form factors, high costs, and limited privacy protection. To address these limitations, lensless cameras have emerged as an alternative. Lensless cameras use thin optical encoders instead of lenses, enabling smaller size, lower cost, and greater design flexibility. These cameras are typically paired with reconstruction algorithms that convert raw captures into recognizable images. However, reconstructed images often contain artifacts, and the reconstruction methods struggle to generalize well to  \nreal-world conditions. Furthermore, existing face datasets do not account for the artifacts present in lensless images. To address this issue, we introduce the Lensless Face Dataset (LFD), a large-scale, real-world lensless face dataset. LFD comprises 21,080 lensless raw measurements, reconstructions, and standard images of faces captured under diverse lighting, angle, and distance. Our key contributions are: (1) Real-world lensless face data: LFD focuses on capturing a diverse face dataset with varying levels of artifacts introduced under different environments; (2) In-the-wild captures: 4,976 images are captured in outdoor settings with varying intensities of natural light and different background patterns; (3) Multiple lensless devices: LFD includes face images collected from three different types of lensless cameras, each with a unique optical encoder mask. We use this hardware diversity to demonstrate generalization across different lensless cameras. Through comprehensive evaluations and data attribute analysis, we show that LFD effectively captures shared features and artifacts across different lensless imaging devices, making it a valuable dataset for advancing lensless face recognition. Our dataset and code are available at [https://jk-junhokim.github.io/lfd_lensless_face_recog/](https://jk-junhokim.github.io/lfd_lensless_face_recog/) .  \nIndex Terms—Lensless Imaging, Face Recognition, Computational Imaging  \n~~ ~~ ✦ ~~ ~~  \n1 INTRODUCTION  \nFACE recognition has become deeply integrated into  \ndaily life with applications such as unlocking smart devices. Beyond personal devices, face recognition is increasingly applied in areas such as robotics, security, and surveillance [1] . Driven by this expanding range of applications, extensive research has focused on leveraging trainable machine learning algorithms using facial data. Asa result, a wide range of specialized face recognition models has been developed to address these diverse applications and scenarios [2], [3], [4] . Most embedded face recognition systems rely on conventional camera modules. However, as applications increasingly demand smaller, lighter, and more cost-effective solutions, traditional lens-based cameras struggle to meet these requirements. This growing tension between miniaturization and imaging performance has become a central imaging challenge.  \nLensless cameras have emerged as a lightweight, lowcost alternative by replacing bulky lenses with ultra-thin optical encoders [5], [6], [7] . Without lenses, these cameras capture raw multiplexed measurements with no local structures intact. Efforts to reconstruct lensless images have led to a range of methods, from convolutional neural networks (CNNs) [8], physics-based neural networks [9] to diffusion models [10], [11], most of which are trained and evaluated on simulated or display-captured data. Despite advances in reconstruction algorithms, current methods still  \n• J. Kim, S.S. Khan, S. Wan, T. Kuye, A. Veeraraghavan are ","cbCairPJxxSyTxUd","https://ap.wps.com/l/cbCairPJxxSyTxUd","pdf",6229887,1,10,"English","en",105,"# Introduction\n# Lensless Face Dataset (LFD)\n# Data Collection Design and Diversity\n# Evaluation and Data Attribute Analysis","[{\"question\":\"Why are lensless cameras useful for face recognition?\",\"answer\":\"Lensless cameras replace bulky lenses with thin optical encoders, enabling smaller size, lower cost, and greater design flexibility for deployment scenarios where compact form factors are required.\"},{\"question\":\"What is the Lensless Face Dataset (LFD) and what does it include?\",\"answer\":\"LFD is a large-scale real-world lensless face dataset containing 21,080 lensless raw measurements, reconstructions, and standard webcam face images.\"},{\"question\":\"How does LFD address real-world challenges in lensless face recognition?\",\"answer\":\"LFD captures diverse artifacts across environments by including controlled indoor conditions and in-the-wild outdoor images, and it introduces hardware diversity by collecting data from three different lensless device types with distinct optical encoder masks.\"}]",1784201541,25,{"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},"lfd-enabling-real-world-lensless-face-recognition-with-a-large-scale-dataset","",{"@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/lfd-enabling-real-world-lensless-face-recognition-with-a-large-scale-dataset/85173/",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},"Why are lensless cameras useful for face recognition?","Question",{"text":75,"@type":76},"Lensless cameras replace bulky lenses with thin optical encoders, enabling smaller size, lower cost, and greater design flexibility for deployment scenarios where compact form factors are required.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the Lensless Face Dataset (LFD) and what does it include?",{"text":80,"@type":76},"LFD is a large-scale real-world lensless face dataset containing 21,080 lensless raw measurements, reconstructions, and standard webcam face images.",{"name":82,"@type":73,"acceptedAnswer":83},"How does LFD address real-world challenges in lensless face recognition?",{"text":84,"@type":76},"LFD captures diverse artifacts across environments by including controlled indoor conditions and in-the-wild outdoor images, and it introduces hardware diversity by collecting data from three different lensless device types with distinct optical encoder masks.","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},[93,97,101,105,110,115,120,123,128,131,134],{"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":21,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]