Low-light image enhancement with MiRNet
- 0 Collaborators
This project demonstrates the use of deep learning for enhancing low-light images. ...learn more
Project status: Published/In Market
Overview / Usage
The project makes use of the MiRNet model (as proposed in Learning Enriched Features for Real Image Restoration and Enhancement) in order to enhance low-light images greatly. It first converts the original model to TensorFlow Lite to make it smaller so that it can fit in smaller devices but at the same time it does not loses out on the end quality.
Methodology / Approach
Low-light image enhancement is practically very useful for people with vision-related problems. It can be used as a general image enhancement tool as well. For this project, I have mainly used TensorFlow Lite since it provides very nice tooling for mobile-based deployments.
Technologies Used
* TensorFlow Lite
* TensorFlow Lite Benchmarking
* Colab Notebooks