This paper from et al at Nvidia combines autoencoders and GANs to bidirectionally transform footage from day to night, winter to summer, real to video-game-ish. Wild! arxiv.org/abs/1703.00848
Conversation
I’ve been following pix2pix for awhile and excited to see if they added time to the net (or are just doing frame by frame)
1
The architecture described in the paper suggests independent processing of each frame. Different arch from pix2pix; closer to CycleGAN.
2
1
Show replies
Great paper. Trying to replicate the street images example. Unable to find the data. It's not cited either. Was it a private data that you've worked on OR any night/day video would do?


