My playground.
For the time being, I will make incompatible changes.
waifu2x: Image Super-Resolution for Anime-Style Art. Also it supports photo models (GAN based models)
The repository contains waifu2x pytorch implementation and pretrained models, started with porting the original waifu2x.
The demo application can be found at
- https://waifu2x.udp.jp/ (Cloud version)
- https://unlimited.waifu2x.net/ (In-Browser version).
I want to watch any 2D video as 3D video on my VR device, so I developed this very personal tool.
iw3 provides the ability to convert any 2D image/video into side-by-side 3D image/video.
cliqa provides low-vision image quality scores that are more consistent across different images.
It is useful for filtering low-quality images with a threshold value when creating image datasets.
Currently, the following two models are supported.
- JPEGQuality: Predicts JPEG Quality from image content
- GrainNoiseLeve: Predicts Noise Level related to photograph and PSNR degraded by that noise
CLI tools are also available to filter out low quality images using these results.
- Python 3 (Works with Python 3.10 or later, developed with 3.10)
- PyTorch
- See requirements.txt
We usually support the latest version. If there are bugs or compatibility issues, we will specify the version.