Encoder train on crawled face or FFHQ

[genforce]

Encoder train on crawled face or FFHQ

[ShenYujun]

Thanks for pointing this out. We will test it following your suggestion.

[zhujiapeng]

Both the generator and encoder were trained using FFHQ datasets, which have already been aligned. Thus, if you want to invert the image from the Web, make sure that you have aligned the image first.

[PXThanhLam]

Thanks for your answer, I will align the image before feeding into network.
Ps: In the perceptual model, did you try to calculate l2 loss in multi layer, instead of layer 22 only ( I calculate l2 loss in multi layer and notice that the result is much better )

[zhujiapeng]

We don't try it on multi-layers. Better reconstruction? or better manipulation? or something else?

[PXThanhLam]

Better Reconstruction, I notice that the mse loss between two image is much smaller when doing perceptual loss in multi-layers, and the reconstruct image look more "realistic". Here is some reconstruct image with and without multi-layer perceptual. ( with 1000 iteration)
Original Image:

Reconstruct with multi-layer perceptual loss:

Reconstruct with original perceptual loss:

Ps : I have try to algin and the result is the same (Like what you see in example above), I currently try to expand your work with styleganv2, will inform you when the work is finish.