AINDNet icon indicating copy to clipboard operation
AINDNet copied to clipboard

Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization (CVPR 2020)

Results 11 AINDNet issues
Sort by recently updated
recently updated
newest added

Nice work. Could you release your training code?

Thank you for your awesome code! I am hoping you might open-source the log files you have from training. Maybe the training and validation loss as a function of epoch...

Good idea and works, but I can't run this code, the checkpoint file is too small and restore error! Is the file named "checkpoint" in SIDDtransfer directory the right file?

I just run the code to test the result on the DnD dataset. Here are the results. I just want to know what is the problem. 0001_01_denoised.png ![image](https://user-images.githubusercontent.com/12149978/90975355-66ad0600-e56e-11ea-8675-434c3fa65fd8.png)

Your work is very good, can you provide the training code

Your paper describes that the noise estimator outputs two noise-level maps of **sigma_4 (?.H/4,W/4,,3)** and sigma_1 (?,H,W,3) for computing the weighted average for feeding into AIN-ResBlocks as well as for...

In your paper, you mentioned that the weight term of the noise-level estimator is empirically determined to 0.05 (i.e., **lambda_ms-asymm = 0.05**). Isn't this typo for **lambda_ms-asymm = 0.5** ???

Could you disclose the training script for your AINDNet for both gaussian and rn?

Hi, thanks for your amazing work. I want to compare my work with yours. Can you provide the number of Parameters and FLOPs of your model?