pith. sign in

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 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Efficient Learned Image Compression without Entropy Coding

eess.IV · 2026-05-22 · unverdicted · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Efficient Learned Image Compression without Entropy Coding eess.IV · 2026-05-22 · unverdicted · none · ref 15

    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.