GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing

TL;DR

GridDehazeNet is an end-to-end CNN that uses attention and multi-scale estimation to improve single image dehazing, outperforming existing methods on synthetic and real images without relying on atmospheric scattering models.

Contribution

It introduces a novel attention-based multi-scale network with a trainable pre-processing module for effective image dehazing, challenging the reliance on traditional atmospheric scattering models.

Findings

Outperforms state-of-the-art dehazing methods on synthetic images

Effective in real-world image dehazing scenarios

Does not depend on atmospheric scattering models

Abstract

We propose an end-to-end trainable Convolutional Neural Network (CNN), named GridDehazeNet, for single image dehazing. The GridDehazeNet consists of three modules: pre-processing, backbone, and post-processing. The trainable pre-processing module can generate learned inputs with better diversity and more pertinent features as compared to those derived inputs produced by hand-selected pre-processing methods. The backbone module implements a novel attention-based multi-scale estimation on a grid network, which can effectively alleviate the bottleneck issue often encountered in the conventional multi-scale approach. The post-processing module helps to reduce the artifacts in the final output. Experimental results indicate that the GridDehazeNet outperforms the state-of-the-arts on both synthetic and real-world images. The proposed hazing method does not rely on the atmosphere scattering model, and we provide an explanation as to why it is not necessarily beneficial to take advantage of the dimension reduction offered by the atmosphere scattering model for image dehazing, even if only the dehazing results on synthetic images are concerned.