search

wyhuai / DDNM

[ICLR 2023 Oral] Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
MIT License
1.16k stars 83 forks source link

simplified model not working for denoising? #13

Closed ohayonguy closed 1 year ago

ohayonguy commented 1 year ago

I am running the following command: python main.py --ni --config celeba_hq.yml --path_y celeba_hq --eta 0.85 --deg "denoising" --sigma_y 0.3 -i demo --add_noise --simplified However there is no noise added to the input signal. I changed the code and added noise after line 306 in guided_diffusion/diffusion.py with: if self.args.add_noise: y = get_gaussian_noisy_img(y, sigma_y) However the results are unsatisfying. Here is one output example: 0_0

When removing --simplified from the command everything works well (with the SVD version). Is this an expected result from the simplified model? Or am I doing something wrong? Thanks

wyhuai commented 1 year ago

What if you try if self.args.add_noise: y = get_gaussian_noisy_img(y, sigma_y*0.25)