5,323
edits
Generative adversarial network: Difference between revisions
→Applications
| Line 41: | Line 41: | ||
[https://arxiv.org/abs/1707.04993 Paper]<br> | [https://arxiv.org/abs/1707.04993 Paper]<br> | ||
MoCoGAN: Decomposing Motion and Content for Video Generation<br> | MoCoGAN: Decomposing Motion and Content for Video Generation<br> | ||
===Video Prediction=== | |||
* [http://openaccess.thecvf.com/content_iccv_2017/html/Liang_Dual_Motion_GAN_ICCV_2017_paper.html Dual Motion GAN] | |||
** Have a frame generator and a motion generator | |||
** Combine the outputs of both generators using a fusing layer | |||
** Trained using a frame discriminator and a motion discriminator. (Each generator are trained with both discriminators) | |||
==Resources== | ==Resources== | ||
* [https://github.com/soumith/ganhacks Tricks for Training GANs] | * [https://github.com/soumith/ganhacks Tricks for Training GANs] | ||