[SUGGESTION] Optimized version for videos
forart opened this issue · comments
Hi there, SwinIR is really cool !
Sice it has been "ported" to VapourSynth (thanks to @HolyWu) some interesting discussions - with tests too - about its effectiveness on videos started:
Seems that the main issue is the processing speed, btw someone argue that the algorithm is not (yet ?) optimized for videos...
Hope that inspires.
Thank you for your advice. We will look at it after CVPR deadline.
I join the request, please make an NCNN-Vulkan implementation when the time appears.