Denoising Autoencoder

Implementation of a denoising autoencoder trained on the RENOIR dataset(MI 3 images).

Setting up locally

pip install -r requirements.txt

Dataset

33x33px patches were taken from the reference and noisy images in the dataset. I've serialised these into TFRecords, which can be downloaded using,

python download_data.py

This will download the train and validation records required for training.

Training and inference

1. For training you can run,

    python train.py -e <num_of_epochs>
   

2. For inference,

    python predict.py -i <input_file> -o <output_file>
   

The model doesn't have a fixed input shape so for smaller images(<400x400px), the entire image vector is feed into the model. For larger images, I've used a window of size 33x33px for generating the output image.

Results

The model was trained for 25 epochs on Google colab's GPU(NVIDIA Tesla k8).

1. Reference:

2. Noisy

3. Denoised

References

1. J. Anaya, A. Barbu. RENOIR - A Dataset for Real Low-Light Image Noise Reduction.(arxiv)
2. Image Restoration Using ConvolutionalAuto-encoders with Symmetric Skip Connections-Xiao-Jiao Mao, Chunhua Shen, Yu-Bin Yang(code)