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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Jia, Chen, Ziling, Wu, Xiaolong, Wang, Lu, Wang, Beibei, Zhang, Lei
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929269038383104
author Li, Jia
Chen, Ziling
Wu, Xiaolong
Wang, Lu
Wang, Beibei
Zhang, Lei
author_facet Li, Jia
Chen, Ziling
Wu, Xiaolong
Wang, Lu
Wang, Beibei
Zhang, Lei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2308_06699
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Neural Super-Resolution for Real-time Rendering with Radiance Demodulation
Li, Jia
Chen, Ziling
Wu, Xiaolong
Wang, Lu
Wang, Beibei
Zhang, Lei
Graphics
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.
title Neural Super-Resolution for Real-time Rendering with Radiance Demodulation
topic Graphics
url https://arxiv.org/abs/2308.06699