WSAMF-Net: Wavelet Spatial Attention-Based MultiStream Feedback Network for Single Image Dehazing

Single image-based dehazing has achieved remarkable progress with the development of deep learning technologies. End-to-end neural networks have been proposed to learn a direct hazy-to-clear image translation to recover the clear structures and edges cues from the hazy inputs. However, the frequency domain information is explored insufficiently and lots of intermediate structure and texture related cues of current dehazing networks are ignored, which limits the performances of current approaches. To handle these limitations mentioned above, a wavelet spatial attention based multi-stream feedback network (WSAMF-Net) is proposed for effective single image dehazing. Specifically, the proposed wavelet spatial attention utilizes both frequency-domain and spatial-domain information to enhance the extracted features for better structures and edges. Meanwhile, an enhanced multi-stream based cross feature fusion strategy, including vertical and horizontal attentions, is proposed to reweight and fuse the intermediate features of each stream to acquire more meaningful aggregated features, while the weight sharing strategy is used to achieve a good trade-off between performance and parameters. Besides, feedback mechanism is also designed to provide strong reconstruction ability. Furthermore, we propose a critical real-world industrial dataset (IDS) with images captured in real-world industrial quarry scenarios for research uses. Extensive experiments on various benchmarking datasets, including both synthetic and real-world datasets, demonstrate the superiority of our WSAMF-Net over state-of-the-art single image dehazing methods. The IDS dataset will be available at https://github.com/XBSong/IDS-Datasethttps://github.com/XBSong/IDS-Dataset.

I. Introduction

Foggy, hazy and dusty conditions commonly exist in real-world scenarios, and images captured in these conditions often suffer from severe degradation of contrast and visibility, which adversely affects the performance of subsequent high-level computer vision tasks, such as classification [40], [41], object tracking [12], [43], and object detection [18], [38]. Therefore, the task of image dehazing [1], [5], [12], [24], [36], [51] has received increasing research attentions. However, due to the severe information degradation of non-homogeneous propriety in haze images, it is a challenging ill-posed problem.