Image-deraining

PyTorch Implementation of MPRNet.
Deep learning model to remove rain from the images.

Results:

This model achieves 26 dB PSNR on Rain100H Dataset.

Input 👉 restored image 👉 ground-truth

More examples are in the Results directory.

Details:

1. This model is trained on Rain Dataset.
2. The model is optimized using two losses: Charbonnier Loss and Laplacian Edge Loss.
3. All the training images were resized to 64x64 to fit them into a single GPU.
4. Learning rate is set to 2e-4 and it is decayed overtime to 1e-6.
5. Trained model is available in Pretrained model directory.