Training image signal processors using intermediate loss functions

The disclosre relates to training image signal processors using an intermediate loss function. In an example method for training image signal processors, a reconstructed image is generated via an image signal processor based on a sensor image. An intermediate loss function is generated based on a comparison of an output of one or more corresponding layers of a computer vision network and a copy ofthe computer vision network. The output of the computer vision network is based on the reconstructed image. An image signal processor is trained based on the intermediate loss function. 本公开涉及使用中间损失函数训练图像信号处理器。在用于训练图像信号处理器的示例方法中，经由图像信号处理器基于传感器图像来生成重建图像。基于计算机视觉网络和计算机视觉网络的副本的一个或多个对应层的输出的比较来生成中间损失函数。计算机视觉网络的输出基于重建图像。基于中间损失函数来训练图像信号处理器。