Saved in:
Bibliographic Details
Main Authors: Cao, Hao, Guo, Wenqi, Qin, Zhijin, Han, Jungong
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.23323
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917523292684288
author Cao, Hao
Guo, Wenqi
Qin, Zhijin
Han, Jungong
author_facet Cao, Hao
Guo, Wenqi
Qin, Zhijin
Han, Jungong
contents Entropy coding is widely used in typical learned image compression (LIC) that converts latents into a compact bitstream. However, entropy coding is typically sequential and becomes the coding latency bottleneck. To overcome it, we present Entropy-Coding Free Learned Image Compression (EF-LIC), a multi-rate framework that generates compact representation by removing statistical and correlation redundancy with low coding latency. First, we introduce unconstrained vector quantization and prove that its index distribution approaches the maximum-entropy bound, yielding minimal statistical redundancy. Second, we propose a context-conditioned autoregressive transform that directly reparameterizes the latents to reduce inter-dependency. Theoretical analysis shows that EF-LIC can remove correlation redundancy as effectively as typical LIC with entropy coding, leading to comparable compression performance. Experiments show EF-LIC achieves up to 67.86% bitrate reduction over MS-ILLM on Kodak with LPIPS. Ablation studies further show EF-LIC matches the compression performance of its entropy-coding based variant while achieving over $3\times$ faster encoding and $5\times$ faster decoding.
format Preprint
id arxiv_https___arxiv_org_abs_2605_23323
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Efficient Learned Image Compression without Entropy Coding
Cao, Hao
Guo, Wenqi
Qin, Zhijin
Han, Jungong
Image and Video Processing
Computer Vision and Pattern Recognition
Entropy coding is widely used in typical learned image compression (LIC) that converts latents into a compact bitstream. However, entropy coding is typically sequential and becomes the coding latency bottleneck. To overcome it, we present Entropy-Coding Free Learned Image Compression (EF-LIC), a multi-rate framework that generates compact representation by removing statistical and correlation redundancy with low coding latency. First, we introduce unconstrained vector quantization and prove that its index distribution approaches the maximum-entropy bound, yielding minimal statistical redundancy. Second, we propose a context-conditioned autoregressive transform that directly reparameterizes the latents to reduce inter-dependency. Theoretical analysis shows that EF-LIC can remove correlation redundancy as effectively as typical LIC with entropy coding, leading to comparable compression performance. Experiments show EF-LIC achieves up to 67.86% bitrate reduction over MS-ILLM on Kodak with LPIPS. Ablation studies further show EF-LIC matches the compression performance of its entropy-coding based variant while achieving over $3\times$ faster encoding and $5\times$ faster decoding.
title Efficient Learned Image Compression without Entropy Coding
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.23323