Video model

VGAN

VGAN, the 2016 Video GAN, generates short clips directly from noise using a spatio temporal GAN. It learns a static background and a moving foreground with a learned mask, then a 3D conv discriminator judges realism in space and time.

Type
Video
Weights
Open

More from MIT Computer Science and Artificial Intelligence Laboratory

3

About MIT Computer Science and Artificial Intelligence Laboratory

1

MIT CSAIL is the largest research laboratory at MIT, formed in 2003 by merging the Laboratory for Computer Science (LCS) and the Artificial Intelligence Laboratory. Housed in the Stata Center, it conducts research across computer science and AI — machine learning, robotics, systems, networking, theory, cryptography, and HCI — and helped pioneer the Web, RSA encryption, and core internet technology.