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.
Abstract (translated)
学习图像压缩（LIC）已经实现了显著的编码效率，其中熵建模通过提供信息先验来减少比特率起着至关重要的作用。现有方法主要利用输入图像内部上下文，然而大规模训练数据中嵌入的丰富外部先验却大多未被充分利用。最近基于字典的熵模型的发展表明，整合外部先验可以显著提高压缩性能。但是，目前的方法将异构外部先验组织在一个级别的字典中，导致了不平衡的利用和有限的表现能力。此外，有效的熵建模不仅需要表现力强的先验，还需要能够解释这些先验的参数估计网络。 为了应对上述挑战，我们提出了HiDE框架，即基于层次字典的熵模型化框架用于学习图像压缩。HiDE将外部先验分解为全局结构和局部细节字典，并通过级联检索进行利用，从而实现对外部信息有条理且高效的使用。此外，该方法引入了一个具有并行多感受野设计的上下文感知参数估计器，以适应性地利用异构上下文来准确估算条件概率。 实验结果表明，在Kodak、CLIC和Tecnick数据集上，HiDE相对于VTM-12.1分别实现了18.5%、21.99%和24.01%的BD率节省。
URL
https://arxiv.org/abs/2603.06766
