A Two-branch Neural Network for Non-homogeneous Dehazing via Ensemble Learning

Recently, there has been rapid and significant progress on image dehazing. Many deep learning based methods have shown their superb performance in handling homogeneous dehazing problems. However, we observe that even if a carefully designed convolutional neural network (CNN) can perform well on large-scaled dehazing benchmarks, the network usually fails on the non-homogeneous dehazing datasets introduced by NTIRE challenges. The reasons are mainly in two folds. Firstly, due to its non-homogeneous nature, the non-uniformly distributed haze is harder to be removed than the homogeneous haze. Secondly, the research challenge only provides limited data (there are only 25 training pairs in NH-Haze 2021 dataset). Thus, learning the mapping from the domain of hazy images to that of clear ones based on very limited data is extremely hard. To this end, we propose a simple but effective approach for non-homogeneous dehazing via ensemble learning. To be specific, we introduce a two-branch neural network to separately deal with the aforementioned problems and then map their distinct features by a learnable fusion tail. We show extensive experimental results to illustrate the effectiveness of our proposed method. The source code is available at https://github.com/liuh127/Two-branch-dehazing.

1. Introduction

Single image dehazing as a low-level vision task has gained widespread attention in recent years. In the natural atmosphere, there are smoke, dust, haze, and other atmospheric phenomena that affect visibility. Pictures taken in these environments are often affected by blurring, color distortion, and low contrast problems. Using these kinds of pictures for classification, image segmentation, and other high-level vision tasks significantly reduces prediction accuracy. Single image dehazing aims to restore a clean output image from a hazy input. Many dehazing methods [14, 23, 28, 30, 36, 38, 43, 44, 47] have been proposed.