Efficient and Accurate Multi-scale Topological Network for Single Image Dehazing

TL;DR

This paper introduces a multi-scale topological neural network for single image dehazing that effectively extracts and fuses features at different scales, leading to improved detail recovery and robustness.

Contribution

It proposes a novel multi-scale topological network with adaptive feature modules for progressive dehazing, enhancing feature extraction and fusion capabilities.

Findings

Outperforms state-of-the-art dehazing methods in experiments

Demonstrates strong fault tolerance and robustness

Effectively recovers image details from hazy images

Abstract

Single image dehazing is a challenging ill-posed problem that has drawn significant attention in the last few years. Recently, convolutional neural networks have achieved great success in image dehazing. However, it is still difficult for these increasingly complex models to recover accurate details from the hazy image. In this paper, we pay attention to the feature extraction and utilization of the input image itself. To achieve this, we propose a Multi-scale Topological Network (MSTN) to fully explore the features at different scales. Meanwhile, we design a Multi-scale Feature Fusion Module (MFFM) and an Adaptive Feature Selection Module (AFSM) to achieve the selection and fusion of features at different scales, so as to achieve progressive image dehazing. This topological network provides a large number of search paths that enable the network to extract abundant image features as well as strong fault tolerance and robustness. In addition, ASFM and MFFM can adaptively select important features and ignore interference information when fusing different scale representations. Extensive experiments are conducted to demonstrate the superiority of our method compared with state-of-the-art methods.