[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82867-en":3,"doc-seo-82867-105":29,"detail-sidebar-cat-0-en-105":83},{"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},82867,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","Glare Mitigation using a Differentiable Unified Glare Rating","Recent differentiable light-transport research extends computer graphics to physical inverse design, where visual discomfort from glare must be optimized rather than merely simulated. Unified Glare Rating (UGR), used in architectural and automotive lighting, is traditionally computed with discrete, binary thresholds, which blocks smooth gradient-based inverse rendering. The paper proposes a continuous, fully differentiable UGR proxy using a PSF-based scattering pass to stabilize low-sample optimization and replace the step function with a tunable sigmoid. The method reduces glare across microgeometry roughening, IOR optimization, and gobo masking while preserving global illumination intent.","Eurographics Symposium on Rendering (2026)  \nI. Gkioulekas and A. Jarabo (Editors)  \nGlare Mitigation using a Differentiable Unified Glare Rating  \nLinas Beresna and Eugene Fiume  \nSimon Fraser University, School of Computing Science, Canada  \narXiv :2607 .04796v 1 [ cs .GR] 6 Jul 2026  \nInput Scene and Target UGR Glare Aware Optimisation Target UGR Actualized  \nFigure 1: Starting from an initial high glare state (left), our differentiable rendering framework jointly optimises material parameters (α , η) and light source distributions to reduce the Unified Glare Rating. By utilising a point spread function and a soft sigmoid to formulate a continuous proxy, the framework smoothly guides the scene until a target ergonomic threshold (e.g., UGR ≤ 17) is reached (right) . Our method selectively mitigates localised glare hotspots while preserving the global illumination and aesthetic intent of the original indoor scene.  \nAbstract  \nRecent research in differentiable light transport extends the utility of computer graphics algorithms beyond traditional image generation, offering powerful tools for physical inverse design. In architectural and automotive applications, visual discomfort from glare is a critical design rating, traditionally quantified by the discrete CIE Unified Glare Rating (UGR) . The standard  \nUGR formulation relies on strict binary thresholds, making it fundamentally incompatible with smooth gradient-based inverse rendering. In this paper, we introduce a continuous, fully differentiable proxy for UGR. To resolve the severe optimisation instabilities caused by Monte Carlo variance at low sample densities, we introduce a differentiable optical scattering pass that simulates the Point Spread Function (PSF) of the human eye to heal fractured evaluation masks. We replace the discrete UGR step function with a tunable sigmoid boundary, enabling gradients to flow smoothly from the psychophysical measure back to the physical scene parameters. We deploy this differentiable framework to systematically reduce glare across three radiometric domains: surface-side microgeometry roughening, boundary-side index of refraction (IOR) optimisation, and source-side emit  \nter gobo masking. By transforming a passive perceptual evaluation into an active loss landscape, our framework provides a robust, physics-based pipeline for optimizing visual comfort in complex global illumination environments.  \nCCS Concepts  \n• Computing methodologies → Ray tracing; Reflectance modeling; • Mathematics of computing → Continuous optimization;  \n© 2026 The Author(s) .  \nProceedings published by Eurographics-The European Association for Computer Graphics.  \nThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.  \n2 of 15 L. Beresna & E. Fiume / Differentiable Glare Mitigation  \n1. Introduction  \nArchitectural and automotive lighting design is fundamentally constrained by the need for human visual comfort. One major artifact that compromises this comfort is glare, defined as a psychophysical perception of excessive brightness that causes annoyance, discomfort, or loss in visual performance. In industry, discomfort glare is standardly quantified by the Unified Glare Rating (UGR), originally established by the International Commission on Illumination (CIE) [CIE95] and formalized in modern workplace lighting standards such as EN 12464-1 [Eur21, Arc24] . The UGR evaluates the discomfort caused by light sources relative to the ambient environment. From a computational perspective, it is critical to define this measure as a function of both the observer viewpoint v and the physical scene description S. Formally, the measure UGR (v, S) is calculated as:  \nUGR (v, S) = 8 log10 0L.2b5 i1 L2~~i~~pω~~2~~ii ! (1)  \nwhere Lb is the background adaptation luminance, Li is the luminance of the ith glare source in the directio","cbCainfaYF55Ocei","https://ap.wps.com/l/cbCainfaYF55Ocei","pdf",15126794,1,15,"English","en",105,"# Introduction\n## Unified Glare Rating and its limitations\n## From forward evaluation to inverse optimization","[{\"question\":\"Which scene parameters does the framework optimize to reduce glare?\",\"answer\":\"The framework jointly optimizes material and lighting parameters, including surface microgeometry roughening, boundary-side index of refraction (IOR), and source-side gobo masking, targeting an ergonomic UGR threshold (e.g., UGR ≤ 17).\"}]",1784183564,38,{"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":78,"head_meta":80,"extra_data":82,"updated_unix":27},"glare-mitigation-using-a-differentiable-unified-glare-rating","",{"@graph":35,"@context":77},[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/glare-mitigation-using-a-differentiable-unified-glare-rating/82867/",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","2026-07-24","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"Which scene parameters does the framework optimize to reduce glare?","Question",{"text":75,"@type":76},"The framework jointly optimizes material and lighting parameters, including surface microgeometry roughening, boundary-side index of refraction (IOR), and source-side gobo masking, targeting an ergonomic UGR threshold (e.g., UGR ≤ 17).","Answer","https://schema.org",{"og:url":51,"og:type":79,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":81,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,127],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":45,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":45,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":45,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":45,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":98,"slug":130},19,"General","general"]