bloc97

Well at first this is just a simple caching method for those small users who frequently access the same data, and it makes the code much cleaner. Instead of storing...

After considering extreme use scenarios, I think a hybrid method would be best (storing common data in memory and all the rest on disk), but then, as you stated, there...

For now, I will add a "purge" method in my API, so people can use a timer or purge the cache by themselves, then I will figure out an automatic...

We have to define "what is upscaling". If you see bicubic upscaling as an higher order expansion of bilinear, this algorithm can also be seen as an enhancement to bilinear...

By your definition most early neural network upscaling algorithms are not upscaling either. Before the discovery of the effectiveness of Transposed Convolutions, most upscaling algorithms such as SRCNN and VDSR...

Sorry but I just don't see the difference between Low Resolution -> Bicubic -> VDSR -> High Resolution and Low Resolution -> Bicubic -> Anime4K -> High Resolution The "Upscaling"...

The smoothing of texture is something that can be taken care of with a better line detection algorithm, which is what we're currently working on. Other upscalers use those better...

Depends on your definition of Super-Resolution too. If you define SR as recovering texture detail, then no, Anime4K is not a texture SR algorithm. However, it can recover lines from...

After some thought and doing some research online, I finally understood why people thought this is not upscaling. I have added a small paragraph at the end of the FAQ...

The Anime4K shader is not a GAN, it was trained using pixel-wise loss. If I remember correctly recent SRGANs have 10M+ parameters while the optimized smaller Anime4K shaders have 1.6k...