HiDE: Hierarchical Dictionary-Based Entropy Modeling for Learned Image Compression

TL;DR

HiDE introduces a hierarchical dictionary-based entropy model that effectively leverages external priors for improved learned image compression, achieving significant bitrate savings over existing methods.

Contribution

The paper proposes a hierarchical dictionary framework and a context-aware parameter estimator to better utilize external priors in learned image compression.

Findings

Achieves up to 24% BD-rate savings on benchmark datasets.

Effectively decomposes priors into global and local dictionaries.

Enhances entropy modeling with structured external information.

Abstract

Learned image compression (LIC) has achieved remarkable coding efficiency, where entropy modeling plays a pivotal role in minimizing bitrate through informative priors. Existing methods predominantly exploit internal contexts within the input image, yet the rich external priors embedded in large-scale training data remain largely underutilized. Recent advances in dictionary-based entropy models have demonstrated that incorporating external priors can substantially enhance compression performance. However, current approaches organize heterogeneous external priors within a single-level dictionary, resulting in imbalanced utilization and limited representational capacity. Moreover, effective entropy modeling requires not only expressive priors but also a parameter estimation network capable of interpreting them. To address these challenges, we propose HiDE, a Hierarchical Dictionary-based Entropy modeling framework for learned image compression. HiDE decomposes external priors into global structural and local detail dictionaries with cascaded retrieval, enabling structured and efficient utilization of external information. Moreover, a context-aware parameter estimator with parallel multi-receptive-field design is introduced to adaptively exploit heterogeneous contexts for accurate conditional probability estimation. Experimental results show that HiDE achieves 18.5%, 21.99%, and 24.01% BD-rate savings over VTM-12.1 on the Kodak, CLIC, and Tecnick datasets, respectively.