期刊
VISUAL COMPUTER
卷 39, 期 8, 页码 3197-3210出版社
SPRINGER
DOI: 10.1007/s00371-023-02951-6
关键词
Rendering; Monte Carlo denoising; Neural networks; Ray tracing
In this paper, a lightweight cascaded network is proposed to denoise 1-spp Monte Carlo images through pixel and kernel prediction methods. Experimental results show that the approach achieves state-of-the-art denoising qualities for 1-spp images at an interactive frame speed.
Monte Carlo (MC) path tracing is known for its high fidelity and heavy computational cost.With the development of neural networks, the kernel-based post-processing method has succeeded in denoising noisy images under low sampling rates, but the complex network structure impedes its deployment in interactive applications. In this paper, we propose a lightweight cascaded network which progressively denoises 1-spp Monte Carlo images through both pixel and kernel prediction methods. A primary denoised image is generated by the pixel prediction network at the first stage, which is then fed to the kernel prediction network to obtain multi-resolution kernels. In addition, to take full advantage of the auxiliary buffers, we introduce a bilateral method during image reconstruction. Experimental results show that our approach achieves state-of-the-art denoising qualities for 1-spp images at an interactive frame speed.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据