deep-image-prior
deep-image-prior copied to clipboard
Image restoration with neural networks but without learning.
Hello, I have run the super-resolution and inpainting codes on the provided examples as well as my own test cases. Noise which is already present in the image i.e. not...
How to run notebook (let's say "restoration") with my uploaded image?
Hi. Can you provide some refs or papers of the skip net used for inpainting? I want to know its structure and the difference between skip-net and unet.
Is it possible to restore image which is corrupted with non-Gaussian noise, e.g. with speckle? I tried using denoising.ipynb, but I got bad results. Corrupted image:  Restored image: 
Hi, In `inpainting.ipynb` the loss is `NAN` from the beginning. However, if I turn off cuda: ``` torch.backends.cudnn.enabled = False torch.backends.cudnn.benchmark = False dtype = torch.FloatTensor ``` All the loss...
Hi Dmitry, First of all, great explanations, codes and repo. Do you intend to create a python package with this method? I believe it would be of great use.
Any Jupyter notebook throws an error: ImportError: cannot import name 'compare_psnr' from 'skimage.measure' (C:\ProgramData\Miniconda3\lib\site-packages\skimage\measure\__init__.py). Tried two versions scikit-image 0.18.2 and scikit-image 0.16.2 (installed from PIP), Windows 10, Python 3.7.10 PyTorch...
I successfully tested your inpainting algorithm for the kate.png and peppers.png on my own image (I changed only this:) `elif ('kate.png' in img_path) or ('peppers.png' in img_path) or ('normal.png' in...
How to run the code?I didn't see any test.