Neural Super-Resolution for Real-time Rendering with Radiance Demodulation

TL;DR

This paper introduces a radiance demodulation-based neural super-resolution method that enhances real-time rendering quality by preserving details and ensuring temporal stability, especially in high magnification scenarios.

Contribution

It proposes a novel radiance demodulation technique combined with a warping module and a frame-recurrent neural network to improve detail preservation and stability in real-time super-resolution rendering.

Findings

Achieves high-quality, temporally stable super-resolution in real-time rendering.

Effectively reduces ghosting artifacts through explicit occlusion marking.

Performs well in 4×4 super-resolution scenarios with detailed textures.

Abstract

It is time-consuming to render high-resolution images in applications such as video games and virtual reality, and thus super-resolution technologies become increasingly popular for real-time rendering. However, it is challenging to preserve sharp texture details, keep the temporal stability and avoid the ghosting artifacts in real-time super-resolution rendering. To address this issue, we introduce radiance demodulation to separate the rendered image or radiance into a lighting component and a material component, considering the fact that the light component is smoother than the rendered image so that the high-resolution material component with detailed textures can be easily obtained. We perform the super-resolution on the lighting component only and re-modulate it with the high-resolution material component to obtain the final super-resolution image with more texture details. A reliable warping module is proposed by explicitly marking the occluded regions to avoid the ghosting artifacts. To further enhance the temporal stability, we design a frame-recurrent neural network and a temporal loss to aggregate the previous and current frames, which can better capture the spatial-temporal consistency among reconstructed frames. As a result, our method is able to produce temporally stable results in real-time rendering with high-quality details, even in the challenging 4 $\times$ 4 super-resolution scenarios.