Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoning

TL;DR

This paper introduces a novel non-homogeneous haze removal network that leverages artificial scene priors and bidimensional graph reasoning to effectively dehaze images with non-uniform haze distribution, outperforming existing methods.

Contribution

It proposes a unique framework combining iterative gamma correction for scene prior enrichment and bidimensional graph reasoning for non-local filtering, pioneering the use of graph reasoning in non-homogeneous haze removal.

Findings

Achieves superior dehazing performance on benchmark datasets.

Effectively models long-range dependencies in spatial and channel dimensions.

Outperforms state-of-the-art algorithms in dehazing and image understanding tasks.

Abstract

Due to the lack of natural scene and haze prior information, it is greatly challenging to completely remove the haze from a single image without distorting its visual content. Fortunately, the real-world haze usually presents non-homogeneous distribution, which provides us with many valuable clues in partial well-preserved regions. In this paper, we propose a Non-Homogeneous Haze Removal Network (NHRN) via artificial scene prior and bidimensional graph reasoning. Firstly, we employ the gamma correction iteratively to simulate artificial multiple shots under different exposure conditions, whose haze degrees are different and enrich the underlying scene prior. Secondly, beyond utilizing the local neighboring relationship, we build a bidimensional graph reasoning module to conduct non-local filtering in the spatial and channel dimensions of feature maps, which models their long-range dependency and propagates the natural scene prior between the well-preserved nodes and the nodes contaminated by haze. To the best of our knowledge, this is the first exploration to remove non-homogeneous haze via the graph reasoning based framework. We evaluate our method on different benchmark datasets. The results demonstrate that our method achieves superior performance over many state-of-the-art algorithms for both the single image dehazing and hazy image understanding tasks. The source code of the proposed NHRN is available on https://github.com/whrws/NHRNet.