Glare Mitigation using a Differentiable Unified Glare Rating

2026-07-06

AI Summary

This work proposes the first fully differentiable surrogate model for the Unified Glare Rating (UGR), overcoming the limitations of traditional UGR’s discrete thresholds that hinder gradient-based inverse rendering optimization. By incorporating a human-eye optical point spread function (PSF) simulation and tunable Sigmoid-smoothed boundaries, the method reformulates glare assessment into a continuous, differentiable loss function. Integrated with differentiable rendering, Monte Carlo light transport, and global illumination optimization, the framework actively suppresses glare by jointly optimizing surface microgeometry, refractive indices, and light source occluders. Experiments demonstrate significant glare reduction across diverse radiometric domains, establishing a physically plausible and gradient-stable pipeline for visual comfort optimization applicable to architectural and automotive lighting design.

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.

Problem

• glare mitigation
• Unified Glare Rating
• differentiable rendering
• visual discomfort
• inverse design

Innovation

• differentiable rendering
• glare mitigation
• Unified Glare Rating (UGR)
• point spread function
• inverse design