5,323
edits
Generative adversarial network: Difference between revisions
→Applications
| Line 47: | Line 47: | ||
** Combine the outputs of both generators using a fusing layer | ** 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) | ** Trained using a frame discriminator and a motion discriminator. (Each generator are trained with both discriminators) | ||
===Video Compression=== | |||
* [https://arxiv.org/pdf/1912.10653.pdf Compression via colorization] | |||
** Colorize with GAN. Only transmit luminance (Y of YUV) | |||
** The paper doesn't say how much bitrate is reduced by removing UV. I suspect it isn't much due to chroma subsampling. | |||
==Resources== | ==Resources== | ||
* [https://github.com/soumith/ganhacks Tricks for Training GANs] | * [https://github.com/soumith/ganhacks Tricks for Training GANs] | ||