基于权值共享核预测网络的实时的Monte Carlo去噪
Real-time Monte Carlo Denoising with Weight Sharing Kernel Prediction Network
摘要：
实时的【形】蒙特卡罗去噪的目的是在严格的时间预算内去除低像素采样率（spp）下的严重噪声。最近，核预测方法使用神经网络来预测每个像素的滤波核，并且已经显示出去除蒙特卡罗噪声的巨大潜力。然而，繁重的计算开销阻碍了这些方法的实时的【形】应用。本文扩展了核预测方法，并提出了一种新的方法去噪非常低的spp（例如，1-spp）以实时的【形】帧速率的蒙特卡罗路径跟踪图像。代替使用神经网络来直接预测核映射，即，每个每像素滤波内核的完整权重，我们预测内核映射的编码，随后是具有用于滤波内核的高质量重构的展开操作的高效解码器。核映射编码产生核映射的紧凑的单通道表示，这可以显著降低核预测网络的吞吐量。此外，我们采用了一个可扩展的核融合模块，以提高去噪质量。所提出的方法保留了核预测方法的去噪质量，同时将1-spp噪声输入的去噪时间大约减半。此外，与最近的神经双边基于网格的实时的【形】去噪器相比，我们的方法受益于基于核的重建的高度并行性，并在相同的时间产生更好的去噪结果。
英文摘要：
Real-time Monte Carlo denoising aims at removing severe noise under low samples per pixel (spp) in a strict time budget. Recently, kernel-prediction methods use a neural network to predict each pixel's filtering kernel and have shown a great potential to remove Monte Carlo noise. However, the heavy computation overhead blocks these methods from real-time applications. This paper expands the kernel-prediction method and proposes a novel approach to denoise very low spp (e.g., 1-spp) Monte Carlo path traced images at real-time frame rates. Instead of using the neural network to directly predict the kernel map, i.e., the complete weights of each per-pixel filtering kernel, we predict an encoding of the kernel map, followed by a high-efficiency decoder with unfolding operations for a high-quality reconstruction of the filtering kernels. The kernel map encoding yields a compact single-channel representation of the kernel map, which can significantly reduce the kernel-prediction network's throughput. In addition, we adopt a scalable kernel fusion module to improve denoising quality. The proposed approach preserves kernel prediction methods' denoising quality while roughly halving its denoising time for 1-spp noisy inputs. In addition, compared with the recent neural bilateral grid-based real-time denoiser, our approach benefits from the high parallelism of kernel-based reconstruction and produces better denoising results at equal time.
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。
