Few-Shot Video-to-Video Synthesis

Re:Few-Shot Video-to-Video Synthesis by Invictus0 on Monday November 04, 2019 @08:11PM (#21448631)

I'd like to see these videos in higher resolution. I have to squint to resolve any detail here.

[ Parent | on HN ]

Re:Few-Shot Video-to-Video Synthesis by chairmanwow on Monday November 04, 2019 @09:46PM (#21449134)

My guess would be that the videos processed in their work are quite small to limit computation time

[ Parent | on HN ]

Re:Few-Shot Video-to-Video Synthesis by p1necone on Monday November 04, 2019 @11:15PM (#21449560)

I imagine this would be much less convincing in higher resolution.

[ Parent | on HN ]

Re:Few-Shot Video-to-Video Synthesis by TeMPOraL on Tuesday November 05, 2019 @01:31AM (#21450193)

It's already not very convincing if you look closer. For instance, look at the way hair behaves (or rather, how it doesn't). Or notice the artifacts around shoes.

[ Parent | on HN ]

Re:Few-Shot Video-to-Video Synthesis by diesal11 on Monday November 04, 2019 @11:51PM (#21449712)

The Paper includes some higher resolution examples which are quite convincing

[ Parent | on HN ]

Re:Few-Shot Video-to-Video Synthesis by p1necone on Tuesday November 05, 2019 @12:02AM (#21449773)

The paper is a PDF file, is there another video component I'm missing?

[ Parent | on HN ]

Re:Few-Shot Video-to-Video Synthesis by rasz on Tuesday November 05, 2019 @10:10PM (#21459420)

You cant, its a hard rule of image/video manipulation papers, results must be 64x64 pixel or smaller.

[ Parent | on HN ]

Re:Few-Shot Video-to-Video Synthesis by anigbrowl on Tuesday November 05, 2019 @12:54AM (#21450012)

I mean that's just a time/GPU power issue.

[ Parent | on HN ]