EF-LIC is a multi-rate learned image compression framework that eliminates entropy coding via unconstrained VQ and autoregressive reparameterization, achieving up to 67.86% bitrate reduction versus MS-ILLM on Kodak with LPIPS while running over 3x faster at encode and 5x at decode.
We compare against the stronger entropy coding implementations in DCVC-RT (Jia et al., 2025)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Efficient Learned Image Compression without Entropy Coding
EF-LIC is a multi-rate learned image compression framework that eliminates entropy coding via unconstrained VQ and autoregressive reparameterization, achieving up to 67.86% bitrate reduction versus MS-ILLM on Kodak with LPIPS while running over 3x faster at encode and 5x at decode.