Variational Denoising Network: Toward Blind Noise Modeling and Removal (NeurIPS, 2019) arXiv
- Ubuntu 16.04, cuda 10.0
- Python 3.6, Pytorch 1.1.0
- More detail (See environment.yml)
- For the Non-IID Gaussian Denosing as described in the paper, please run demo_test_simulation.py.
- For real-wormd image denoising task, please run demo_test_benckmark.py. The model was trained on the SIDD Medium Dataset (320 noisy and clean paris).
- Prepare the dataset following the code in the floder datasets. Data link: Waterloo Exploration Database, CBSD432 and CImageNet400.
- Train VDN using train_simulation.py or train_benchmark.py.