Learning-based techniques have recently been shown to be effective for denoising Monte Carlo rendering methods. However, there remains a quality gap to state-of-the-art handcrafted denoisers. In this paper, we propose a deep residual learning based method that outperforms both state-of-the-art handcrafted denoisers and learning-based denoisers. Unlike the indirect nature of existing learning-based methods (which e.g., estimate the parameters and kernel weights of an explicit feature based filter), we directly map the noisy input pixels to the smoothed output. Using this direct mapping formulation, we demonstrate that even a simple-and-standard ResNet and three common auxiliary features (depth, normal, and albedo) are sufficient to achieve high-quality denoising. This minimal requirement on auxiliary data simplifies both training and integration of our method into most production rendering pipelines. We have evaluated our method on unseen images created by a different renderer. Consistently superior quality denoising is obtained in all cases.

中文翻译：

---

深度残差学习用于消除蒙特卡洛效果图

近来，基于学习的技术已被证明对消除蒙特卡洛渲染方法有效。但是，最先进的手工去噪器仍存在质量差距。在本文中，我们提出了一种基于深度残差学习的方法，该方法优于最先进的手工去噪器和基于学习的去噪器。与现有的基于学习的方法（例如，估计基于显式特征的过滤器的参数和内核权重）的间接性质不同，我们直接将嘈杂的输入像素映射到平滑的输出。使用这种直接映射公式，我们证明即使是简单标准的Res​​Net以及三个常见的辅助功能（深度，法线和反照率）也足以实现高质量的去噪。对辅助数据的最低要求简化了我们的方法的培训，并将其集成到大多数生产渲染管道中。我们已经对由其他渲染器创建的看不见的图像评估了我们的方法。在所有情况下，都能获得始终如一的优质降噪效果。