https://github.com/vilmacio/depixelate

Upscale an illustration and increase details
https://github.com/vilmacio/depixelate

black-white enhance illustration image-processing no-ai-used opencv python srcnn upscaling waifu2x

Last synced: 3 months ago
JSON representation

Upscale an illustration and increase details

• Host: GitHub
• URL: https://github.com/vilmacio/depixelate
• Owner: vilmacio
• License: mit
• Created: 2022-07-19T02:24:18.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2023-09-10T23:09:20.000Z (about 1 year ago)
• Last Synced: 2024-05-02T02:25:45.220Z (6 months ago)
• Topics: black-white, enhance, illustration, image-processing, no-ai-used, opencv, python, srcnn, upscaling, waifu2x
• Language: Python
• Homepage: https://vilmacio.github.io/depixelate-app/
• Size: 218 KB
• Stars: 25
• Watchers: 2
• Forks: 3
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Depixelate

Upscaling and enhance low resolution images.



## Usage

First of all, you might want to check out the [Online Demo](https://vilmacio.github.io/depixelate-app/). Once done, let's code.

```console

$ pip install depixelate

```

```python

import cv2

import depixelate

original_image = cv2.imread('image.jpg')

result = depixelate.apply(original_image, 7, 600)

```

### Params

The **apply** method accepts 3 parameters:

- **Image (Required)**: Original image to be changed.

- **Weight (Optional)**: Indicates the power of the gaussian-blur algorithm. The higher the value, the more shape distortion. It must be between 1 and 10. Default value is 6.

- **Width Scale (Optional)**: Indicates the width of the output image. Default value is 800.

## Limitations

Depixelate library helps with logos and some graphics, but it doesn't help when maximum sharpness and detail is needed.


In the majority of cases, you'll want to improve the quality of low resolution images (about 300 pixels wide or less). Otherwise you might be a little disappointed.

## Plans

- [ ] [Depixelizing Pixel Art](https://johanneskopf.de/publications/pixelart/paper/pixel.pdf) Implementation