Using uniform lattice grids for quantization and entropy-gradient latent shifting improves rate-distortion performance of off-the-shelf neural codecs by 1-3% without retraining.
Joint autoregressive and hier- archical priors for learned image compression,
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
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Exploiting Latent Properties to Optimize Neural Codecs
Using uniform lattice grids for quantization and entropy-gradient latent shifting improves rate-distortion performance of off-the-shelf neural codecs by 1-3% without retraining.