A single rate-distortion autoencoder with a discrete latent space and an autoregressive prior outperforms prior learned video codecs without motion compensation.
http://ultravideo
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Video Compression With Rate-Distortion Autoencoders
A single rate-distortion autoencoder with a discrete latent space and an autoregressive prior outperforms prior learned video codecs without motion compensation.