MIRNet-TFJS 
This repository shows the TFJS model conversion and inference processes for the for the MIRNet model as proposed by Learning Enriched Features for Real Image Restoration and Enhancement by Zamir et al. This model is capable of enhancing low-light images upto a great extent.
Model training code and pre-trained weights are provided by Soumik through this repository.
A bit about the architecture
The MIRNet presents a novel architecture with the collective goals of maintaining high-resolution representations through the entire network, and receiving strong contextual information from the low-resolution representations.
The core of this approach is a multi-scale residual block containing the following key elements:
- parallel multi-resolution convolution streams for extracting multi-scale features
- information exchange across the multi-resolution streams
- spatial and channel attention mechanisms for capturing contextual information
- attention based multi-scale feature aggregation.
Framework of MIRNet
The figure above shows the framework of the proposed network MIRNet that learns enriched feature representations for image restoration and enhancement.
About the notebooks
MIRNet_Saved_Model.ipynb
This notebook shows the the process of downloading pre-trained weights for the MIRNet model and saving it as a SavedModel.
MIRNet_TFJS.ipynb
This notebook shows the the process of converting the SavedModel to the TFJS format we built in the prequel notebook for the MIRNet model. It also shows performing optimizations on this.
MIRNet_Inference.ipynb
This notebook shows the the process of inferencing for the MIRNet model on a couple of low light photos.