Adaptive Learned Image Compression with Graph Neural Networks

2026-03-26

AI Summary

This work proposes an adaptive image compression framework based on graph neural networks to overcome the limitations of fixed receptive fields and static connectivity in existing methods, which struggle to model spatially varying redundancy in images. By introducing a dual-scale graph construction and a content-driven dynamic adjacency mechanism, the framework enables flexible and learnable receptive fields that adapt to local image content. This approach transcends the rigid architectural constraints of conventional CNNs or Transformers. Experimental results demonstrate state-of-the-art performance, achieving BD-rate savings of 19.29%, 21.69%, and 18.71% over VTM-9.1 on the Kodak, Tecnick, and CLIC datasets, respectively.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Graph-based Machine Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Efficient image compression relies on modeling both local and global redundancy. Most state-of-the-art (SOTA) learned image compression (LIC) methods are based on CNNs or Transformers, which are inherently rigid. Standard CNN kernels and window-based attention mechanisms impose fixed receptive fields and static connectivity patterns, which potentially couple non-redundant pixels simply due to their proximity in Euclidean space. This rigidity limits the model's ability to adaptively capture spatially varying redundancy across the image, particularly at the global level. To overcome these limitations, we propose a content-adaptive image compression framework based on Graph Neural Networks (GNNs). Specifically, our approach constructs dual-scale graphs that enable flexible, data-driven receptive fields. Furthermore, we introduce adaptive connectivity by dynamically adjusting the number of neighbors for each node based on local content complexity. These innovations empower our Graph-based Learned Image Compression (GLIC) model to effectively model diverse redundancy patterns across images, leading to more efficient and adaptive compression. Experiments demonstrate that GLIC achieves state-of-the-art performance, achieving BD-rate reductions of 19.29%, 21.69%, and 18.71% relative to VTM-9.1 on Kodak, Tecnick, and CLIC, respectively. Code will be released at https://github.com/UnoC-727/GLIC.

Problem

• image compression
• spatial redundancy
• adaptive modeling
• receptive field
• global redundancy

Innovation

• Graph Neural Networks
• Learned Image Compression
• Adaptive Connectivity
• Content-Adaptive Compression
• Dual-Scale Graphs