Foveated light culling

Abstract

In this paper, we propose a novel Foveated Light Culling (FLC) method to efficiently approximate global illumination for foveated rendering in virtual reality applications. The key idea is to cull the virtual point lights (VPLs) in accordance with their contribution to the visual perception, which makes the loss of details caused is imperceptible to the human eyes. Based on this idea and the features of human visual system (HVS), we calculate the contribution of each VPL according to samples generated from a perceptual importance map. By estimating the local visibility between VPLs and samples, our method can greatly improve the performance during the process of evaluating contributions. Our method is able to produce high-quality single-bounce diffuse-to-diffuse indirect illumination in the foveal region at real-time frame rate while supporting dynamic scenes and light sources. Furthermore, the experiments show that our approach makes a good balance between foveal quality and render efficiency.