about

[liuliuliu11]

Thanking you for sharing work~

Pluralistic-Inpainting/model/network.py

Line 39 in 1ca1855

class ResEncoder(nn.Module):

-L137 In probabilistic framework, don't consider Ic, just look at Im, In forward propagation, Im passes through the modules (block0 -> encoder i -> infer_prior i -> prior) in turn. What I am puzzled is that the latent code of Im is the output of 'encoder i' or 'infer_prior i' ? in other words， What is the role of infer_prior i?
In addition, is prior module used to get the distribution?

Looking forward to your reply~

[lyndonzheng]

Hi @liuliuliu11, in the two_paths functions, we respectively consider both I_c and I_m in the top and bottom path, where the former is used to enforce the distribution belong a prior distribution, and the latter tries to infer the missing regions' distribution. However, inferring the distribution based only on the visible regions I_m is much more difficult than inferring the distribution from the original missing ground truth I_c. Therefore, more residual blocks are heaped up in the bottom inference network for I_m.