Project DetailsThis project focuses on the issue of real image denoising cleaning noise that is created during the process of capturing the image. In the first part of the project, we designed a CNN, based on RIDNet architecture. In the second part of the project we wish to improve the result of the network, on a dataset it hasnt seen before. I.e., improve the generalization capability of the network. To achieve this goal, we have created datasets with synthetic noise, that aspired to be as similar as possible to real noise.
In order to train this model, we have created 4 datasets, each of them constructed of different ratio of real noise image and synthetic noise image. Each dataset is about 500,000 images. We tested the models on 2 test sets, SIDD and NAM. The results were measured using 2 evaluation methods: PSNR and SSIM. Other than that, we examined the effect of the different dataset on the results visually. We saw that we managed to improve the results on datasets that were captured by different cameras and different settings, but the results for the dataset it has been trained on, has significantly worsen.
