HiDE: Hierarchical Dictionary-Based Entropy Modeling for Learned Image Compression
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910044131426304 |
|---|---|
| author | Xiong, Haoxuan Xu, Yuanyuan Zhu, Kun Wang, Yiming Ye, Baoliu |
| author_facet | Xiong, Haoxuan Xu, Yuanyuan Zhu, Kun Wang, Yiming Ye, Baoliu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_06766 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HiDE: Hierarchical Dictionary-Based Entropy Modeling for Learned Image Compression Xiong, Haoxuan Xu, Yuanyuan Zhu, Kun Wang, Yiming Ye, Baoliu Image and Video Processing Computer Vision and Pattern Recognition Multimedia 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. |
| title | HiDE: Hierarchical Dictionary-Based Entropy Modeling for Learned Image Compression |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2603.06766 |