Open Source GLSL (OpenGL Shading Language) Video Upscalers

A video player that enhances the quality of a hand-drawn image using Anime4K's high-performance scaling algorithm. This program is a video player written in the Python programming language using the PySimpleGUI graphical user interface library, an mpv media player, and the Anime4K scaling algorithm . Anime Player is designed to play video and audio files and includes functions such as opening files, URLs and folders, setting image scaling parameters using the Anime4K algorithm, creating an mpv config for watching videos using the Anime4K algorithm on Android, viewing help and information about tuning the algorithm. The player also has support for frame interpolation using SVP. You need to install SVP and VapourSynth to work.

ACNet is a CNN algorithm, implemented by Anime4KCPP, it aims to provide both high-quality and high performance. This GLSL implementation can be used in MPV player, it is cross-platform. Windows users can also use Anime4KCPP DirectShow Filter for MPC-HC/BE or potplayer. Download the glsl file and MPV player. Copy glsl to the root directory of MPV. Create a file named mpv.conf in the root directory of MPV, and add the following statement (Assume the glsl file name is ACNet.glsl). When playing the video, press Shift + i and then 2 to check if it is enabled.

Anime4K is an upscaler specifically for anime style. This repository is an implementation of Anime4K in TouchDesigner that can be used to upscale low-resolution textures to higher textures. Reduced texture loss, aliasing and banding.

An AviSynth+ implementation of some Super-Resolution Convolutional Neural Networks. Independent luma/chroma upscaling and chroma resampling. Two modes for Video/Photography and Line Art. KrigBilateral option for chroma upscaling/resampling. mpv user shaders of all models for real-time upscaling. Copy AiUpscale.avsi and the Shaders folder to the AviSynth+ plugins folder. The low resolution images were generated using the bicubic filter with Catmull-Rom settings, which is the method commonly used for training super-resolution networks, including those tested here. Note however that as an exception to this, the Anime4K models were trained using the average area downsampling method. The AiUpscale models used for all datasets were the "Photo" models, except for the Manga109 dataset for which the "LineArt" models were used. In the same way, the Waifu2x cunet model was used for the Manga109 dataset, and the upconv_7 model for the rest.