https://github.com/soumik12345/mirnet

Tensorflow implementation of MIRNet for Low-light image enhancement
https://github.com/soumik12345/mirnet

computer-vision deep-learning image-restoration low-light-image-enhancement mirnet streamlit streamlit-webapp tensorflow tensorflow2

Last synced: 9 days ago
JSON representation

Tensorflow implementation of MIRNet for Low-light image enhancement

• Host: GitHub
• URL: https://github.com/soumik12345/mirnet
• Owner: soumik12345
• License: apache-2.0
• Created: 2020-11-28T21:44:41.000Z (about 4 years ago)
• Default Branch: master
• Last Pushed: 2021-09-18T04:54:30.000Z (over 3 years ago)
• Last Synced: 2024-12-25T03:21:33.261Z (22 days ago)
• Topics: computer-vision, deep-learning, image-restoration, low-light-image-enhancement, mirnet, streamlit, streamlit-webapp, tensorflow, tensorflow2
• Language: Jupyter Notebook
• Homepage: https://huggingface.co/spaces/keras-io/Enhance_Low_Light_Image
• Size: 27.9 MB
• Stars: 112
• Watchers: 4
• Forks: 37
• Open Issues: 5
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# MIRNet

[![](https://static.streamlit.io/badges/streamlit_badge_black_white.svg)](https://share.streamlit.io/soumik12345/mirnet/app.py)

Tensorflow implementation of the MIRNet architecture as proposed by [Learning Enriched Features for Real Image

Restoration and Enhancement](https://arxiv.org/pdf/2003.06792v2.pdf).

**Lanuch Notebooks:** [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/soumik12345/MIRNet/HEAD)

**Wandb Logs:** [https://wandb.ai/19soumik-rakshit96/mirnet](https://wandb.ai/19soumik-rakshit96/mirnet)

**Blog Post:** [https://keras.io/examples/vision/mirnet/](https://keras.io/examples/vision/mirnet/)

**TFLite Variant of MIRNet:** [https://github.com/sayakpaul/MIRNet-TFLite](https://github.com/sayakpaul/MIRNet-TFLite).

**TFLite Models on Tensorflow Hub:** [https://tfhub.dev/sayakpaul/lite-model/mirnet-fixed/dr/1](https://tfhub.dev/sayakpaul/lite-model/mirnet-fixed/dr/1).

**Tensorflow JS Variant of MIRNet:** [https://github.com/Rishit-dagli/MIRNet-TFJS](https://github.com/Rishit-dagli/MIRNet-TFJS).

![](./assets/mirnet_architecture.png)

![](./assets/lol_results.gif)

## Pre-trained Weights

- **Trained on 128x128 patches:** [https://drive.google.com/file/d/1sUlRD5MTRKKGxtqyYDpTv7T3jOW6aVAL/view?usp=sharing](https://drive.google.com/file/d/1sUlRD5MTRKKGxtqyYDpTv7T3jOW6aVAL/view?usp=sharing)

- **Trained on 256x256 patches:** [https://drive.google.com/file/d/1sUlRD5MTRKKGxtqyYDpTv7T3jOW6aVAL/view?usp=sharing](https://drive.google.com/file/d/1sUlRD5MTRKKGxtqyYDpTv7T3jOW6aVAL/view?usp=sharing)

## Citation

```

@misc{

    2003.06792,

    Author = {Syed Waqas Zamir and Aditya Arora and Salman Khan and Munawar Hayat and Fahad Shahbaz Khan and Ming-Hsuan Yang and Ling Shao},

    Title = {Learning Enriched Features for Real Image Restoration and Enhancement},

    Year = {2020},

    Eprint = {arXiv:2003.06792},

}

```