Open Source C# Video Upscalers

Anime4KSharp is a .Net Core library that implements bloc97's Anime4K Algorithm version 0.9 and 1.0 RC2. The Algorithm is executed on the CPU, but utilizing all available CPU Cores. This yields to a conversion time of "only" 4432 ms when upscaling from 1080p to 2160p. This time could possibly be reduced with further optimization. Images are processed in four phases that are executed on a pixel- per- pixel basis. Each phase takes a input image and renders it to a output image. This makes it easy to port the algorithm (back) to GLSL fragment shaders. As bloc97 described in his pseudo-preprint, the Anime4K algorithm is actually quite simple.

A simple program with a UI for exporting video to png and encoding png images to video using FFmpeg, for the purpose of upscaling. A simple program with a UI for exporting video to png and encoding png images to video using FFmpeg, for the purpose of upscaling. This program does not upscale your video, it's a tool to be used to save time for your upscaling process. Instead of opening CMD yourself and navigating to your ffmpeg location and then enter the command, this program does all that for you. Saves a lot of time when working with multiple videos. It does however require some knowledge of FFmpeg commands for you to be able to customize your encoding command for your needs. Encoding presets can be fully modified and comes with some decent default settings for x264 encodes. I plan to add more features in the future, this was just something I rushed together quickly in 2 days and has been extremely useful for me ever since.

This project generates hand-written digits from the MNIST dataset using WGAN architecture. While debugged, a few lingering issues may remain, if you encounter any please submit them and they will be resolved. The sources and features of the project can be found in the wiki. Before use, one should verify that the network architecture is as-desired. This may be done with the GUI to the right of the number display. The "Default" button resets the network to hard-coded values which I have verified function. The "Reset" button sets the ACTIVE network to whatever architecture is displayed. In order to change which network is displayed, use the "Critic [1] or Generator [0]" checkbox. To begin training the network, press the "Train" button, after which you may use the "Clear" button to reset the average error and average percent correct value textboxes. In order to use the project on an alternative dataset, one must replace the MNIST files, then rewrite IO.FindNextNumber.

A set of tools for slicing a texture atlas to individual components and merging back. These tools simplify the approach for upscaling a texture atlas. Manually select some tiles in the texture atlas (that are placed in difficult positions) Add them to a json file following this pattern: json file; you can use any image editing tool such as GIMP to manually select and inspect the location, width and height of each selection. Run the tool with the split; this will automatically create a folder with separate files from the selections, as well a [basefilename]_sliced.png file containing the texture without the sliced files. Manually upscale all the resulting files with the correct transparency / seamless mode, including the [basefilename]_sliced.png from the previous step. it is important to use the same scale factor for all the files. you can leave some of the files unscaled (including the basefile).