This is a project which just move the official project N2V to tensorflow. The N2V is referring to the approach for image denoising in the paper "Noise2Void - Learning Denoising from Single Noisy Images". Please cite them if you think this project can help you.
for using this code, you have to do something else:
please refer to tensorflow for details.
this project only implement the code to load the BSD68 dataset. And you can follow the two steps to prepare the dataset.
- open BSD68_reproducibility_data.zip in web viewer and download it to the folder "data".
- uncompress the "BSD68_reproducibility_data.zip" in "data" folder.
then, you just input the following sentence to train it.
python train.py <gpu_id>
python predict.py <gpu_id> saved_weight_path
final psnr on BSD68 is 27.91 dB while it is 27.71 dB in the paper.