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.

翻译：物理成像的减慢速度受到采用的重要取样技术的严重影响。 在本文中,我们提出一个新的在线框架,以学习空间变化密度模型,使用随机射线样本的单一小型神经网络进行空间变化密度模型学习。为了完成这项任务,我们提出一个新的封闭式密度模型,称为正常的厌食性球球球混合体,能够用少量参数表达复杂的辐照场。我们的框架以渐进的方式学习分布,不需要任何热量阶段。由于我们密度模型的缩写和表达方式,我们的框架可以完全在GPU上实施,使其能够产生高质量的图像,而计算资源有限。</s>