[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:
- http://forum.doom9.org/showthread.php?p=1956669#post1956669
- https://forum.videohelp.com/threads/399360-so-where-s-all-the-Topaz-Video-Enhance-AI-discussion/page13#post2634990
Seems that the main issue is the processing speed, btw someone argue that the algorithm is not (yet ?) optimized for videos...
About speed: @xinntao may help to implement an NCNN-Vulkan (as already done for Real-ESGRAN)...
About video optimizations: a collaboration with @ding3820 of MIMO-VRN project may help...
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.
See VRT(https://github.com/JingyunLiang/VRT) and RVRT (https://github.com/JingyunLiang/RVRT) for transformer-based video restoration (sr, deblurring, denoising, frame interpolation and space-time VSR)