Generating neurosimulated frames using one or more neural networks

Generating a frame of neurosimulation using one or more neural networks is disclosed. Apparatuses, systems, and techniques are disclosed for generating one or more images using one or more neural networks based at least in part on one or more spatially independent features within the one or more images. In at least one embodiment, one or more neural networks determine spatially independent information and spatially related information for one or more images, and process the spatially independent information and the spatially related information to generate one or more spatially independent features and one or more spatially related features within the one or more images. 公开了使用一个或更多个神经网络来生成神经模拟的帧，具体公开了使用一个或更多个神经网络至少部分地基于一个或更多个图像内的一个或更多个空间无关特征来生成一个或更多个图像的装置、系统和技术。在至少一个实施例中，一个或更多个神经网络确定一个或更多个图像的空间无关信息和空间相关信息，并处理空间无关信息和空间相关信息以生成一个或更多个图像内的一个或更多个空间无关特征和一个或更多个空间相关特征。