I have some old footage (circa 2002) from when I used to race. Recorded on in car camcorder at 720 x 480 29.97 (it was older Sony or Canon).
For the heck of it, I thought I’d send it thru Video AI with 2X upscale with stabilization (rolling shutter and jittery motion unchecked), motion Deblur (Themis), frame interpolation (Apollo) enabled, AI model Proteus - Enhance MQ.
Screenshot of original footage:
Screenshot of Video AI output:
I think Video AI can do better, but I’m not really sure how?
Did some research on QTGMC … it seems people spend “years” fiddling with command line type settings and LOTS of trial and error. Sadly I don’t really have that much free time to be fiddling to much with software. Is there an easier approach or presets?
Qtgmc does not have a command line with Hybrid or Staxrip which are software. and it is with qtgmc that you will deinterlace best. You have to forget vai to deinterlace.