RIFE AI interpolation
Please be aware that RIFE support is currently at BETA stage.
RIFE is a Real-time Intermediate Flow Estimation algorithm based on a neural network named IFNet, that can directly estimate the intermediate flows from images.
- Original RIFE implementation and demos
- RIFE algorithm ported to ncnn/Vulkan
- A Vapoursynth filter based on RIFE/ncnn
- very high quality of the intermediate frames
- runs completely on GPU
- very slow (comparing to SVP's interpolation method), do not expect it to run in real time unless you have a high-end video card and want to interpolate low-resolution video (up to 720p).
- only frame rate doubling is supported
- SVP 4.5.210 is required
- Install an additional package via SVP menu -> Utilities -> Add. programs and features, called [VPS_64] FIDE AI interpolation engine, restart SVP
- You'll notice a new video profile called RIFE AI interpolation added.
- browse for a video file
- choose a RIFE video profile
- start transcoding!
Alternatively if you own a high-end video card you may try it in a real-time playback:
- start playback in mpv (preferably) or VLC, DirectShow players may also work via Vapoursynth Filter (VPSF)
- !! IT WON'T WORK VIA AVISYNTH !!
- manually switch to the RIFE video profile (it will be in the Other profiles sub-menu)
- be patient ;)
RIFE on CUDA
CUDA implementation is much faster (like 2-3 times faster) than Vulkan, however it depends on really huge Python library which can't be bundled with SVP. Moreover it only works with transcoding and doesn't seems work in a real-time mpv/VPSF.
If you want to give it a try please follow this instructions (warning: you have to be an advanced user :D).