Learned Image Compression with Frequency Feature Interaction and Non-local Cross-similarity Prior

Read full text Summarise with VIRAT
Authors: Jian Wang, Qiang Ling
Cited by: 0
References: 45

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Recently, learned image compression models have achieved better compression performance than traditional non-learning image compression standards. Those learned models usually utilize spatial self-attention and Convolutional Neural Network (CNN) to extract non-local and local features and generate the latent representation. However, previous methods adopt a linear layer to fuse non-local and local features and lack the flexibility to adaptively adjust feature weights and capture complex non-linear interactions between distinct feature representations. Additionally, how to more effectively compress the latent representation based on its channel similarity characteristics remains unexplored. To solve the above issues, we propose a novel image compression method with frequency feature interaction and non-local cross-similarity prior. More specifically, we extend the previous spatial self-attention module and alternately use spatial and channel self-attention modules to extract non-local spatial and channel features, respectively, and depth-wise convolution is utilized to extract local features. As local features focus on high-frequency detail information and non-local features concentrate on low-frequency structural information, we propose a frequency interaction module (FIM) that generates two weight maps to dynamically fuse non-local and local features. Moreover, we observe the non-local cross-similarity in different channels of the latent representation, which indicates that different channels share similar non-local semantic and structural information, but have distinct local detail information. So, we design a dual transformer entropy model to emphasize non-local features and remove local features. Experiment results validate our method achieves promising compression performance on the Kodak, CLIC, and Tecnick datasets.

Fields of Study & Subjects

Advanced Data Compression Techniques Video Coding and Compression Technologies Advanced Neural Network Applications

Publication details

Journal / source
ACM Transactions on Multimedia Computing Communications and Applications
Volume
22
Issue
5
Pages
1–22
Publication date
25 March 2026
Language
EN