Giters

wyhuai / DDNM

[ICLR 2023 Oral] Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

How to improve the mask-shift results

gsdndeer opened this issue · comments

commented

Hi authors, thanks for releasing this great work!

I am trying to use mask-shift technique on my image-to-image translation task in medical images. I trained my diffusion model with crop data augmentation. But I can’t get the smooth results like yours. Is there any way to improve it?

The following are the results of my task.

This is the generated result of the first patch.
Screen Shot 2023-03-13 at 5 45 33 PM

Then, I shift the patch right and leave a half of overlapped regions with the previous patch.
tmp0_64

This is the result of the step 2.
Screen Shot 2023-03-13 at 5 45 50 PM

commented

Hi, you may check these points:

  • Can your framework do normal-size inpainting tasks?
  • Is the masked region correctly placed?