arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.16115cs.CVcs.GR
收藏

基于自适应采样和核池的两阶段Monte Carlo去噪

Two-Stage Monte Carlo Denoising with Adaptive Sampling and Kernel Pool

The University of Sydney(悉尼大学);Tencent AI Lab(腾讯AI实验室)

Tiange Xiang, Hongliang Yuan, Haozhi Huang, Yujin Shi

摘要:

蒙特卡罗路径跟踪器在低采样计数下呈现噪声图像序列。虽然在对这些序列进行去噪方面已经取得了很大的进展,但是现有的方法仍然受到空间和临时伪影的影响。本文针对蒙特卡罗渲染中存在的问题,提出了一种基于自适应采样策略的两级去噪算法。在第一阶段中,在动态调整每像素采样数(spp)的同时,我们重用计算来生成应用于自适应渲染图像的额外去噪内核。而不是直接预测的像素级内核,我们节省了开销的复杂性,从一个公共的内核池,可以动态更新,以适应输入信号的内核插值。在第二阶段,我们设计了位置感知池和语义对齐操作,以提高时空稳定性。我们的方法首先在Mitsuba渲染器渲染的10个合成场景上进行基准测试,然后在我们自建的基于RTX的渲染器渲染的3个额外场景上进行验证。我们的方法在数值误差和视觉质量方面都优于最先进的同行。

英文摘要:

Monte Carlo path tracer renders noisy image sequences at low sampling counts. Although great progress has been made on denoising such sequences, existing methods still suffer from spatial and temporary artifacts. In this paper, we tackle the problems in Monte Carlo rendering by proposing a two-stage denoiser based on the adaptive sampling strategy. In the first stage, concurrent to adjusting samples per pixel (spp) on-the-fly, we reuse the computations to generate extra denoising kernels applying on the adaptively rendered image. Rather than a direct prediction of pixel-wise kernels, we save the overhead complexity by interpolating such kernels from a public kernel pool, which can be dynamically updated to fit input signals. In the second stage, we design the position-aware pooling and semantic alignment operators to improve spatial-temporal stability. Our method was first benchmarked on 10 synthesized scenes rendered from the Mitsuba renderer and then validated on 3 additional scenes rendered from our self-built RTX-based renderer. Our method outperforms state-of-the-art counterparts in terms of both numerical error and visual quality.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑