Video Super Resolution

Image Super Resolution (ISR) is a way to improve quality of low resolution images and upscale it. This project utilizes that and enables it to be used for videos.
Explore the docs »

View Demo · Report Bug · Request Feature

Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Prerequisites
   • Installation
3. Usage
4. Roadmap
5. Contributing
6. License
7. Contact

About The Project

The project was developed using Python 3.6. The aim of this is to scale up a video and increase the quality of it. Using Image Super Resolution, each frame is scaled up. The various deep learning methods allow for quality to improve even though the video is scaled up. You can learn more about ISR here.

Currently this has only been tested on mp4 videos.

Demo

Original	Video Super Resolution

Built With

• ISR
• OpenCV
• ffmpeg

Getting Started

Follow the steps to get started

Prerequisites

• ffmpeg
  • Mac:

    • brew install ffmpeg

  • Linux:

    •   sudo apt install ffmpeg

Python 3.6 might be required. Take a look at pyenv for managing multiple Python versions. *Python 3.7.9-amd64 (32 bit python version will not work) was tested and found to work. Newer versions of python (>3.10) cannot install the required version of tensorflow.

Installation

Binary: Install the V0 release from the releases section on the github side panel.

Source code:

1. Clone the repo

   git clone https://github.com/viraatdas/video-super-resolution.git

2. Install modules

   pip install -r requirements.txt

Usage

Example: python enhance.py example_videos/video_short.mp4

Example: python enhance.py example_videos/video_short.mp4 --zoom 3 --remove_noise (Note: If you installed the binary, use the same commands, but instead of "python enhance.py" use "enhance.exe" then the other arguments.)

positional arguments:
  filename              Required positional argument

optional arguments:
  -h, --help            show this help message and exit
  --zoom ZOOM           Specifies scaling factor of video (default is 2x)
  --remove_noise        If specified, then will denoise the video
  --output_filename     OUTPUT_FILENAME
                        Specify output filename
  --version             show program's version number and exit

Roadmap

See the open issues for a list of proposed features (and known issues). Feel free to add to it.

Contributing

Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

License

Distributed under the MIT License. See LICENSE for more information.

Contact

Viraat Das - @therealviraat - viraat.laldas@gmail.com

README template based on othneildrew