Path‐based Monte Carlo Denoising Using a Three‐Scale Neural Network,Computer Graphics Forum

当前位置： X-MOL 学术 › Comput. Graph. Forum › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Path‐based Monte Carlo Denoising Using a Three‐Scale Neural Network
Computer Graphics Forum ( IF 2.7 ) Pub Date : 2020-12-30 , DOI: 10.1111/cgf.14194
Weiheng Lin _{1,

2} , Beibei Wang _{1,

2} , Jian Yang _{1,

2} , Lu Wang ₃ , Ling‐Qi Yan ₄

Affiliation

Monte Carlo rendering is widely used in the movie industry. Since it is costly to produce noise-free results directly, Monte Carlo denoising is often applied as a post-process. Recently, deep learning methods have been successfully leveraged in Monte Carlo denoising. They are able to produce high quality denoised results, even with very low sample rate, e.g. 4 spp (sample per pixel). However, for difficult scene configurations, some details could be blurred in the denoised results. In this paper, we aim at preserving more details from inputs rendered with low spp. We propose a novel denoising pipeline that handles three-scale features pixel, sample and path to preserve sharp details, uses an improved Res2Net feature extractor to reduce the network parameters and a smooth feature attention mechanism to remove low-frequency splotches. As a result, our method achieves higher denoising quality and preserves better details than the previous methods. CCS Concepts • Computing methodologies → Neural network; Ray tracing;

中文翻译：

使用三尺度神经网络的基于路径的蒙特卡罗去噪

Monte Carlo 渲染在电影行业中被广泛使用。由于直接产生无噪声结果的成本很高，因此蒙特卡罗去噪通常用作后处理。最近，深度学习方法已成功用于蒙特卡罗去噪。即使采样率非常低，例如 4 spp（每像素采样），它们也能够产生高质量的去噪结果。然而，对于困难的场景配置，去噪结果中的一些细节可能会模糊。在本文中，我们的目标是从使用低 spp 渲染的输入中保留更多细节。我们提出了一种新颖的去噪管道，它处理像素、样本和路径的三尺度特征以保留清晰的细节，使用改进的 Res2Net 特征提取器来减少网络参数，并使用平滑的特征注意机制来去除低频斑点。因此，与以前的方法相比，我们的方法实现了更高的去噪质量并保留了更好的细节。CCS 概念 • 计算方法 → 神经网络；光线追踪；

更新日期：2020-12-30

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11