why doesn't LR encoding network g_θ need to be invertible?

[qiufengmama]

[martin-danelljan]

Because it is only used for conditioning. Please see the paper if you want the in depth explanation and derivation.

[nachifur]

@martin-danelljan Thank you for your wonderful work. The place I am puzzled is: why the variance of z is 0, and the network can still output a better psnr super-resolution image, because this does not add high-frequency details to the network. I look forward to your reply.

[nachifur]

My other problem is that when training to DF2K_4x, the verification output is completely black when training to 160000. It is normal for 80000. For more iterations, the output is all black. This seems to be abnormal. Can you explain this?

0_000080000_h050_s1: 0_000160000_h050_s1:

The drop in loss seems to be correct.