Alternative way to concatenate AU conditions with input image about ganimation HOT 4 CLOSED

On my previous paper I checked a bunch of methods and concatenating had the best tradeoff performance-overhead.

from ganimation.

A possible alternative way to do it is concatenating AU conditions as a vector with image unrolled into a vector and replace the first convolutional layer with a fully-connected layer.

This produces much many parameters especially when image is high resolution, so it seems not so good.

from ganimation.

There exists a large literature on image conditional generation (from noise+conditioning) check them out, you should find some useful insights on conditional representation for non-image like inputs.

from ganimation.

@albertpumarola
As you say, there is a lot of ways for image conditional generation.
Why did you choose the aforementioned way?
Did you follow the way adopted in pix2pix?

from ganimation.