Low Light Image Enhancement

A simple VUE.js application that enhances low light images privately locally in the browser (demo).

This repository contains the code to convert the Pytorch implementation of the Self-Calibrated Illumination (SCI) Learning Framework to the ONNX format and the code to run the model in the browser inside a Vue.js application.

If you want to know more about the processes and steps involved in how to build the vue.js application and how to run the model locally in the browser have a look at my blog post.

Installation and Usage

Project Setup for the model conversion

Install python dependencies

cd model
pip install -r requirements.txt

Convert the model to ONNX

python transform_to_onnx_and_test.py

Project Setup for the frontend

cd frontend
npm install

Compile and Hot-Reload for Development

npm run dev

Compile and Minify for Production

npm run build

Lint with ESLint

npm run lint

Screen.Recording.2024-01-26.at.08.34.30.mov

Acknowledgements

The model code and weights are based on the Pytorch implementation of the following CVPR paper.