Skip to content

Latest commit

 

History

History
59 lines (34 loc) · 1.84 KB

README.md

File metadata and controls

59 lines (34 loc) · 1.84 KB

My playground.

For the time being, I will make incompatible changes.

waifu2x

waifu2x/README.md

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

iw3

iw3/README.md

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

cliqa/README.md

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.

Install

Installer for Windows users

For developers

Dependencies

  • Python 3 (Probably works with Python 3.9 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.