5,323
edits
Generative adversarial network: Difference between revisions
→Video Compression
| Line 48: | Line 48: | ||
** 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=== | ===Image and Video Compression=== | ||
* [https://arxiv.org/pdf/1912.10653.pdf | * [http://openaccess.thecvf.com/content_ICCV_2019/html/Agustsson_Generative_Adversarial_Networks_for_Extreme_Learned_Image_Compression_ICCV_2019_paper.html Image Compression] | ||
* [https://arxiv.org/pdf/1912.10653.pdf Video compression via colorization] | |||
** Colorize with GAN. Only transmit luminance (Y of YUV) | ** Colorize with GAN. Only transmit luminance (Y of YUV) | ||
** The paper claims 72% BDBR reduction compared to HM 16.0. | ** The paper claims 72% BDBR reduction compared to HM 16.0. | ||