Hierarchical Feature Fusion With Mixed Convolution Attention for Single Image Dehazing

Single image dehazing, which aims at restoring a haze-free image from its correspondingly unconstrained hazy scene, is a fundamental yet challenging task and has gained immense popularity recently. However, the images recovered by some existing haze-removal methods often contain haze, artifacts, and color distortions, which severely degrade the visual quality and have negative impacts on subsequent computer vision tasks. To this end, we propose a network combining multi-scale hierarchical feature fusion and mixed convolution attention to progressively and adaptively enhance the dehazing performance. The haze levels and image structure information are accurately estimated by fusing multi-scale hierarchical features, thus the model restores images with less remaining haze. The proposed mixed convolution attention mechanism is capable of reducing feature redundancy, learning compact and effective internal representations and highlighting task-relevant features, thus, it can further help the model estimate images with sharper textural details and more vivid colors. Furthermore, a deep semantic loss is also proposed to highlight essential semantic information in deep features. The experimental results show that the proposed method outperforms state-of-the-art haze removal algorithms.

Automated summary

Single image dehazing is a fundamental and challenging task in computer vision, and has gained significant attention. Existing haze-removal methods often suffer from issues such as degraded visual quality and color distortions. To address these issues, we propose a network with multi-scale hierarchical feature fusion and mixed convolution attention, which enhances the dehazing performance progressively and adaptively.