Glare Mitigation using a Differentiable Unified Glare Rating
2026-07-06 • Graphics
Graphics
AI summaryⓘ
The authors created a way to measure glare (uncomfortable brightness) smoothly so computers can adjust designs to reduce it. Traditional glare measures use sharp cutoffs that make it hard for algorithms to improve lighting automatically. By using math tricks like a soft boundary and modeling how the eye blurs light, their method lets glare scores change gently with design tweaks. They tested this approach by reducing glare in three different lighting aspects, helping make spaces and cars more visually comfortable through computer optimization.
differentiable light transportUnified Glare Rating (UGR)inverse renderingMonte Carlo variancePoint Spread Function (PSF)sigmoid functionindex of refraction (IOR)microgeometry rougheningemitter gobo maskingglobal illumination
Authors
Linas Beresna, Eugene Fiume
Abstract
Recent 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 UGR 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 emitter 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.