Re:Few-Shot Video-to-Video Synthesis
by alexcnwy on Tuesday November 05, 2019 @04:15AM
(#21450856)
The flicker would be a challenge but you can use something like DeOldify [1] or super resolution [2] on the frame sequence to improve the colour and resolution... although you may get some weird artifacts between frames using image models rather than models built for video.
Generally video models are quite far behind image models because they're so much higher dimensional (much more computationally expensive and expensive to annotate) but I'm sure it's a matter of time before someone releases a DeOldify type model for video (if one doesn't exist already).
Re:Few-Shot Video-to-Video Synthesis
by yboris on Tuesday November 05, 2019 @09:19AM
(#21452525)
For super resolution of video, the best thing I've come across is TecoGAN which uses adjacent frames for extra information, creating a consistent flow between frames.
Generally video models are quite far behind image models because they're so much higher dimensional (much more computationally expensive and expensive to annotate) but I'm sure it's a matter of time before someone releases a DeOldify type model for video (if one doesn't exist already).
[1] https://github.com/jantic/DeOldify [2] https://github.com/idealo/image-super-resolution