T-Net: Deep Stacked Scale-Iteration Network for Image Dehazing

Haze reduces the visibility of image content and leads to failure in handling subsequent computer vision tasks. In this paper, we address the problem of single image dehazing by proposing a dehazing network named T-Net, which consists of a backbone network based on the U-Net architecture and a dual attention module. Multi-scale feature fusion can be achieved by using skip connections with a new fusion strategy. Furthermore, by repeatedly unfolding the plain T-Net, Stack T-Net is proposed to take advantage of the dependence of deep features across stages via a recursive strategy. To reduce network parameters, the intra-stage recursive computation of ResNet is adopted in our Stack T-Net. We take both the stage-wise result and the original hazy image as input to each T-Net and finally output the prediction of the clean image. Experimental results on both synthetic and real-world images demonstrate that our plain T-Net and the advanced Stack T-Net perform favorably against state-of-the-art dehazing algorithms and show that our Stack T-Net could further improve the dehazing effect, demonstrating the effectiveness of the recursive strategy.

I. Introduction

Haze is a common atmospheric phenomenon that not only has a serious adverse effect on human visual perception, but also has a serious impact on the performance of modern computer vision systems for various visual tasks, such as image classification, object detection and video surveillance. Since hazy conditions such as fog, aerosols, sands and mist can scatter and adsorb light, images taken in a hazy environment suffer from many different degradations such as blurred visibility, color cast, reduced contrast and halo artifacts. Therefore, it is crucial to develop effective solutions to reduce the impact of image degeneration caused by environmental conditions through dehazing.