基于归一化各向异性球面高斯的在线神经路径引导
Online Neural Path Guiding with Normalized Anisotropic Spherical Gaussians
AI总结：
本文提出一种基于归一化各向异性球面高斯混合模型的在线神经路径引导框架，通过单个小型神经网络渐进学习空间变化密度，无需预热阶段，可完全在GPU上实现并在有限资源下生成高质量图像。
摘要：
基于物理的渲染的方差缩减速度在很大程度上受所采用的采样技术的影响。本文提出了一种新颖的在线框架，利用随机光线样本和单个小型神经网络来学习空间变化的密度模型。为实现这一目标，我们提出了一种新颖的闭式密度模型，称为归一化各向异性球面高斯混合模型，该模型能够以少量参数表达复杂的辐照度场。我们的框架以渐进方式学习分布，并且不需要任何预热阶段。由于密度模型表示紧凑且表达能力强，我们的框架可以完全在GPU上实现，从而在有限的计算资源下生成高质量图像。
英文摘要：
The variance reduction speed of physically-based rendering is heavily affected by the adopted importance sampling technique. In this paper we propose a novel online framework to learn the spatial-varying density model with a single small neural network using stochastic ray samples. To achieve this task, we propose a novel closed-form density model called the normalized anisotropic spherical gaussian mixture, that can express complex irradiance fields with a small number of parameters. Our framework learns the distribution in a progressive manner and does not need any warm-up phases. Due to the compact and expressive representation of our density model, our framework can be implemented entirely on the GPU, allowing it produce high quality images with limited computational resources.
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。
