Repository navigation
How to train the model with the image2image mode #21
Description
Thank for your code.
I want to train this model with my dataset, and could i use this model for my image, I have a dataset with pairs of original image and noisy image, noisy images have some kind of noises like motion blur, salt and pepper noise and exposure noise for example.
Activity
explainingai-code commentedon Jul 24, 2024
Hi,
In this repo, only gaussian noise is added progressively. It seems that based on your requirement, this paper, might be exactly what you are looking for. They have an implementation online - https://github.com/arpitbansal297/Cold-Diffusion-Models , so the deblurring diffusion(with some modifications) should fit your use case.
dangdinh17 commentedon Jul 24, 2024
oh thank you, i will try it