Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/lucchetto/superimage
Sharpen your low-resolution pictures with the power of AI upscaling
https://github.com/lucchetto/superimage
android compose image-processing mnn real-esrgan super-resolution upscaling
Last synced: 3 months ago
JSON representation
Sharpen your low-resolution pictures with the power of AI upscaling
- Host: GitHub
- URL: https://github.com/lucchetto/superimage
- Owner: Lucchetto
- License: gpl-3.0
- Archived: true
- Created: 2023-02-01T21:14:42.000Z (almost 2 years ago)
- Default Branch: master
- Last Pushed: 2023-11-09T19:26:12.000Z (about 1 year ago)
- Last Synced: 2024-09-25T22:40:39.812Z (3 months ago)
- Topics: android, compose, image-processing, mnn, real-esrgan, super-resolution, upscaling
- Language: Kotlin
- Homepage:
- Size: 79.3 MB
- Stars: 1,378
- Watchers: 20
- Forks: 83
- Open Issues: 30
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# SuperImage
**Sharpen your low-resolution pictures with the power of AI upscaling**
SuperImage is a neural network based image upscaling application for Android built with the [MNN deep learning framework](https://github.com/alibaba/MNN) and [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN).The input image is processed in tiles on the device GPU, using a pre-trained Real-ESRGAN model. The tiles are then merged into the final high-resolution image. This application requires Vulkan or OpenCL support and Android 7 or above
Or get the latest APK from the [Releases Section](https://github.com/Lucchetto/SuperImage/releases/latest).
## đź Samples
## đ Benchmarks
Results on Qualcomm Snapdragon 855 (Vulkan)
| Mode | Input resolution | Output resolution | Execution time |
| ------------- | ---------------- | ----------------- | ----------------- |
| 4x (generic) | 1920x1080 | 3840x2160 | 3 minutes |
| 16x (generic) | 1920x1080 | 7680x4320 | 11 minutes |
| 16x (drawing) | 1920x1080 | 7680x4320 | 3 mins 42 seconds |## đą Screenshots
Â
 Â
Â## đŹ Community
You can join the [Telegram group](https://t.me/super_image) for support, discussions about AI image processing, and off-topic stuff## ĺ Contribute
You can submit feedbacks or bug reports by [opening an issue](https://github.com/Lucchetto/SuperImage/issues/new). Pull requests are welcome !## đ TODO
- Support images with transparency
- Batch processing
- Web and desktop versions## đ Credits
- Pre-trained models and original implementation from [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN)
- Pictures by [Satoshi Hirayama](https://www.pexels.com/photo/yasaka-pagoda-in-kyoto-7526805), [Skitterphoto](https://www.pexels.com/photo/food-japanese-food-photography-sushi-9210), [夊ćąă˛ăŞă](https://www.pixiv.net/en/artworks/103802719) and [Ryutaro Tsukata](https://www.pexels.com/photo/an-illuminated-lanterns-on-the-street-5745029)## âď¸ License
SuperImage is licensed under the [GNU General Public License v3.0](https://www.gnu.org/licenses/gpl-3.0.html)