May 2019
Intermediate to advanced
272 pages
7h 19m
English
Vid2Vid is an amazing technique that tackles the problem of video-to-video synthesis. Vid2Vid is an extension of the Pix2PixHD GAN, which is the same network that we implemented in this book that outperforms several state-of-the-art competing systems.
Vid2Vid was developed by Ting-Chun Wang et al. and is described in the paper, Video-to-Video Synthesis, published at NeurIPS in 2018. One of the most notable achievements of Vid2Vid is that it produced the first interactive AI-rendered virtual world. The following screenshot shows a person driving through this AI-rendered virtual world:

For more information ...
Read now
Unlock full access