CTHD-Net: CNN-Transformer hybrid dehazing network via residual global attention and gated boosting strategy.

• A novel Residual Global Attention (RGA) to flexibly focus on different types of information, such as thin haze regions and thick haze regions. • A CNN-Transformer architecture to capture both detail texture information and global context information. • A Gated Strength-Operation-Subtract Boosting (GSOS) strategy to effectively integrate cross-layer feature information, thereby overcoming the problem of incomplete noise removal and detail loss. Single image dehazing is one of crucial tasks in the field of computer vision. However, existing methods are challenged on how to handle unevenly distributed haze, capture global contextual information, and filter noise while preserving details. To overcome these limitations, a novel dehazing network with residual global attention and gated boosting strategy based on a CNN-Transformer hybrid architecture (CTHD-Net) is proposed. Firstly, a feature encoder with a residual global attention (RGA) module is presented to improve the representation capability of the entire network by adaptively assigning different weights to feature maps. Subsequently, a CNN-Transformer hybrid architecture is designed to enhance the features encoding via the improved Swin-transformer and to capture the long-range dependencies among features by shifted-window Multi-head Self-attention. Finally, an effective Gated Strength-Operation-Subtract (GSOS) Boosting decoder is developed to reuse the key information required for image reconstruction in the shallow features, while effectively preventing haze noise. Extensive evaluation demonstrates that our proposed CTHD-Net significantly outperforms the previous state-of-the-arts in terms of quantity and quality. The source code has been made available at https://github.com/RC-Qiao/CTHD-Net. [ABSTRACT FROM AUTHOR]