Foveated Photon Mapping
PubDate: August 2021
Teams: Beihang University；University of California Santa Barbara
Writers: Xuehuai Shi; Lili Wang; Xiaoheng Wei; Ling-Qi Yan
Abstract
Virtual reality (VR) applications require high-performance rendering algorithms to efficiently render 3D scenes on the VR head-mounted display, to provide users with an immersive and interactive virtual environment. Foveated rendering provides a solution to improve the performance of rendering algorithms by allocating computing resources to different regions based on the human visual acuity, and renders images of different qualities in different regions. Rasterization-based methods and ray tracing methods can be directly applied to foveated rendering, but rasterization-based methods are difficult to estimate global illumination (GI), and ray tracing methods are inefficient for rendering scenes that contain paths with low probability. Photon mapping is an efficient GI rendering method for scenes with different materials. However, since photon mapping cannot dynamically adjust the rendering quality of GI according to the human acuity, it cannot be directly applied to foveated rendering. In this paper, we propose a foveated photon mapping method to render realistic GI effects in the foveal region. We use the foveated photon tracing method to generate photons with high density in the foveal region, and these photons are used to render high-quality images in the foveal region. We further propose a temporal photon management to select and update the valid foveated photons of the previous frame for improving our method’s performance. Our method can render diffuse, specular, glossy and transparent materials to achieve effects specifically related to GI, such as color bleeding, specular reflection, glossy reflection and caustics. Our method supports dynamic scenes and renders high-quality GI in the foveal region at interactive rates.
