CLG-INet: Coupled Local-Global Interactive Network for Image Restoration

What is it about?

We propose a lightweight image restoration network (CLG-INet) based on CNN-Transformer interaction, which can efficiently couple the local and global information. Extensive experiments demonstrate that CLG-INet significantly boosts performance on various image restoration tasks, such as deraining, deblurring, and denoising.

Featured Image

Why is it important?

Our model is hierarchically built with a "sandwich-like" structure of coupling blocks, where each block contains three layers in sequence (CNN-Transformer-CNN). The Transformer layer is designed with two core modules: Dynamic Bi-Projected Attention (DBPA), which performs dual projection with large convolutions across windows to capture long-range dependencies, and Gated Non-linear Feed-Forward Network (GNFF), which reconstructs mixed feature information. In addition, we introduce interactive learning, which fuses local features and global representations in different resolutions to the maximum extent.