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

TL;DR

This paper introduces T-Net and Stack T-Net, novel deep neural networks with recursive and multi-scale features, for improved image dehazing, outperforming existing methods on synthetic and real-world datasets.

Contribution

Proposes a new recursive, multi-scale dehazing network called Stack T-Net that enhances dehazing performance with fewer parameters.

Findings

Stack T-Net outperforms state-of-the-art dehazing algorithms.

Recursive strategy improves dehazing effectiveness.

Both T-Net and Stack T-Net perform well on synthetic and real images.

Abstract

Hazy images reduce the visibility of the image content, and haze will lead to failure in handling subsequent computer vision tasks. In this paper, we address the problem of 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. And it can achieve multi-scale feature fusion 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. In order to reduce network parameters, the intra-stage recursive computation of ResNet is adopted in our Stack T-Net. And we take both the stage-wise result and the original hazy image as input to each T-Net and finally output the prediction of 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 the 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.