---
tags:
- image-restoration
- deblurring
- sharpening
- scratch-removal
- deep-learning
- computer-vision
- tensorflow
- keras
license: mit
language: en
library_name: keras
datasets: []
metrics:
- psnr
- ssim
widget:
- src: assets/revive_banner.png
example_title: ReviveAI Example Image
inference: true
---
# ReviveAI โจ
Restore your memories. AI-powered image deblurring, sharpening, and scratch removal.
---
## ๐ About ReviveAI
ReviveAI leverages the power of Artificial Intelligence to breathe new life into your old or degraded photographs. Whether it's blurriness from camera shake, general lack of sharpness, or physical damage like scratches, ReviveAI aims to restore clarity and detail, preserving your precious moments.
This project utilizes state-of-the-art deep learning models trained specifically for image restoration tasks. Our goal is to provide an accessible tool for enhancing image quality significantly.
---
## ๐ฅ Key Features
* **โ
Completed - Image Sharpening:** Enhances fine details and edges for a crisper look.
* **โ
Completed - Scratch Removal:** Intelligently detects and inpaints scratches and minor damages on photographs.
* **๐ ๏ธ Work-in-progress - Image Colorization(Coming Soon):** Adds realistic color to grayscale images.
---
## โจ Before & After Showcase
See the results of ReviveAI in action!
| Examples | Task Performed |
| :-----------------------------------------: | :----------------- |
| 
| Image Sharpening |
| 
| Image Sharpening |
| 
| Scratch Removal |
| 
| Scratch Removal |
---
## ๐ ๏ธ Tech Stack
ย
ย
ย
ย
---
## ๐ Implementation Status
Track the development progress of ReviveAI's key features and components:
| Feature / Component | Status | Notes / Remarks (Optional) |
| :--------------------------- | :----------------------- | :------------------------- |
| Image Deblurring/Sharpening | โ
Completed | Core model functional |
| Scratch Removal | โ
Completed | Core model functional |
| Image Colorization | ๐ง In Progress | Model integration underway |
---
## ๐ Getting Started
Follow these steps to get ReviveAI running on your local machine or in a Jupyter/Kaggle notebook.
### 1. Prerequisites
Ensure you have the following installed:
- Python 3.8 or above
- `pip` (Python package manager)
- Git (for cloning the repository)
- [Hugging Face CLI (optional)](https://huggingface.co/docs/huggingface_hub/quick-start)
- Jupyter Notebook or run on [Kaggle](https://kaggle.com) / [Google Colab](https://colab.research.google.com)
---
### 2. Clone the Repository
```bash
git clone https://github.com/Zummya/ReviveAI.git
cd ReviveAI
```
---
### 3. Set Up the Environment
We recommend using a virtual environment:
```bash
python -m venv env
source env/bin/activate # On Windows: env\Scripts\activate
pip install -r requirements.txt
```
---
## ๐ฏ Load Pretrained Models
All models are hosted on the Hugging Face Hub for convenience and version control.
### ๐น Load Image Sharpening Model
```python
from huggingface_hub import hf_hub_download
from tensorflow.keras.models import load_model
model_path = hf_hub_download(
repo_id="Sami-on-hugging-face/RevAI_Deblur_Model",
filename="SharpeningModel_512_30Epochs.keras"
)
model = load_model(model_path, compile=False)
```
---
### ๐น Load Scratch Removal Model
```python
from huggingface_hub import hf_hub_download
from tensorflow.keras.models import load_model
model_path = hf_hub_download(
repo_id="Sami-on-hugging-face/RevAI_Scratch_Removal_Model",
filename="scratch_removal_test2.h5"
)
model = load_model(model_path, compile=False)
```
---
### ๐ Folder Structure
```bash
ReviveAI/
โ
โโโ README.md
โโโ .gitignore
โโโ requirements.txt
โ
โโโ models/
โ โโโ sharpening_model.txt # Hugging Face URL
โ โโโ scratch_removal_model.txt # Hugging Face URL
โ
โโโ notebooks/
โ โโโ scratch_removal_notebook.ipynb
โ โโโ sharpening_model_notebook.ipynb
โ
โโโ before_after_examples/
โ โโโ sharpening/
โ โโโ scratch_removal/
โ
โโโ assets/
โ โโโ revive banner.png, showcase images etc.
```
---
## ๐งช Training & Running the Models
ReviveAI includes end-to-end Jupyter notebooks that allow you to both **train** the models from scratch and **test** them on custom images.
### ๐ Available Notebooks
| Notebook | Description |
| -------- | ----------- |
| `sharpening_model_notebook.ipynb` | Train the sharpening (deblurring) model + Run predictions |
| `scratch_removal_notebook.ipynb` | Train the scratch removal model + Run predictions |
---
### ๐ก Notebook Features
Each notebook includes:
- ๐ง **Model Architecture**
- ๐ **Data Loading & Preprocessing**
- ๐๏ธ **Training Pipeline** (with adjustable hyperparameters)
- ๐พ **Saving & Exporting Weights**
- ๐ **Evaluation**
- ๐ผ๏ธ **Visual Demo on Custom Images**
---
### ๐ผ๏ธ Quick Test Function (for inference)
To run a prediction on a new image (after training or loading a model), use:
```python
def display_prediction(image_path, model):
import cv2
import matplotlib.pyplot as plt
import numpy as np
img = cv2.imread(image_path)
img = cv2.resize(img, (256, 256)) / 255.0
input_img = np.expand_dims(img, axis=0)
predicted = model.predict(input_img)[0]
plt.figure(figsize=(10, 5))
plt.subplot(1, 2, 1)
plt.imshow(img[..., ::-1])
plt.title("Original Input")
plt.axis("off")
plt.subplot(1, 2, 2)
plt.imshow(predicted)
plt.title("Model Output")
plt.axis("off")
plt.show()
```
Run the function like this:
```python
display_prediction("your_image_path.jpg", model)
```
---
> โ
Tip: If you don't want to train from scratch, you can directly load pretrained weights from Hugging Face (see [๐ฏ Load Pretrained Models](#-load-pretrained-models)) and skip to the testing section.
ReviveAI
Made with โค๏ธ at ISTE-VIT
---