Perceptual Model for Foveated Rendering With Illuminance Demodulation.

Abstract

Foveated rendering exploits the non-uniform acuity of human vision to allocate computational resources more efficiently by reducing image fidelity in the peripheral field of view. While existing perceptual models for foveated rendering focus primarily on spatial resolution and contrast sensitivity, they overlook the perceptual asymmetry between direct and indirect illumination. In this work, we introduce a novel perceptual model that incorporates illuminance demodulation to account for this distinction. Our model adaptively modulates the foveation rate based on the relative contributions of direct and indirect illumination. Building on this model, we develop a practical rendering framework that separately applies tailored foveation strategies to direct and indirect illumination effects. Quantitative metrics and user studies confirm that our method maintains perceptual equivalence to full-resolution rendering. The sparse rendering stage achieves a $2.18\times$ to $7.10\times$ speedup, contributing to an overall acceleration of $1.71\times$ to $3.26\times$.