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

TL;DR

This paper introduces a two-branch neural network that employs ensemble learning to effectively address the challenges of non-homogeneous image dehazing, especially with limited training data.

Contribution

The paper proposes a novel two-branch neural network architecture with a learnable fusion tail for non-homogeneous dehazing, improving performance on limited data scenarios.

Findings

Effective non-homogeneous dehazing demonstrated on benchmark datasets.

Two-branch architecture outperforms single-branch models.

Learnable fusion enhances feature integration for better dehazing results.

Abstract

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.