I face the problem of learning a mapping (or a translation) $f: (x,\theta) \to x^\prime$, where $x, x^\prime$ are images, $\theta$ is the parameters of a neural network.
I know the models for parameters-to-parameters mapping (meta-learning), images-to-images mapping (style transfer, auto-encoders). But I have no idea which deep learning models can do parameters-to-images mapping.
Any suggestion is welcomed.