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.

I. Introduction

Images captured in hazy conditions often contain unclear content and degraded structural details. These low-visibility images are a hindrance to multiple subsequent high-level tasks [1]–[5], including autonomous driving, video surveillance, and visual object tracking. As a fundamental yet challenging technique, single image dehazing, which aims at restoring haze-removed images with less remaining haze, sharper structure details and vivid colors from low-visibility scenarios, will be beneficial to the application of these high-level tasks. Thus, single image dehazing has become an increasingly popular research topic recently.