Update Apr 16 2021: Made 16-0-4-1 sharper
Update Mar 5 2021: Improved 8-0-4-1 (LineArt is in the 7z archive unmodified)
FSRCNN, extended with local residual learning and recursive blocks.
All networks have been trained with --distort=True. Means they can reduce slight compression artifacts. There is a version of this network trained to remove strong compression artifacts here.
LineArt version has been trained using a dataset that only consists of flat lines, so it may look like an oil painting on a more natural type of content. Need a better dataset.
If you placed this shader in the same folder as your mpv.conf
, then your config should look like this (regardless of the operating system):
profile=gpu-hq
glsl-shader="~~/FSRCNNX_x2_8-0-4-1.glsl"
For people who use image metrics for evaluation of quality - I recommend using SSIM with Mean Absolute Deviation pooling (instead of default mean pooling). VIFp is also quite good. Don't recommend - PSNR and MS-SSIM (including DSSIM and SSIMULACRA2).