RIFE AI interpolation

From SmoothVideo Project
Jump to navigation Jump to search

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.

Credits:

Pros:

  • very high quality of the intermediate frames
  • runs completely on GPU

Cons:

  • 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

Installation

  • 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.

Svp-rife.png

Usage

  • 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).

Credits: https://github.com/HolyWu/vs-rife