A linear transform trained with end-to-end rate-distortion optimization beats the DCT and prior data-driven transforms on residual block compression.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Optimal Linear Block Transform by Rate Distortion Minimization
A linear transform trained with end-to-end rate-distortion optimization beats the DCT and prior data-driven transforms on residual block compression.