Transform coding in a VQ-VAE latent space, instead of pixel space, yields 45% bitrate savings over MS-ILLM at equal FID for images and 65.3% DISTS-based bitrate savings over PLVC for video at ultra-low bitrates.
Evc: Towards real-time neural image compression with mask decay,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression
Transform coding in a VQ-VAE latent space, instead of pixel space, yields 45% bitrate savings over MS-ILLM at equal FID for images and 65.3% DISTS-based bitrate savings over PLVC for video at ultra-low bitrates.