Towards Domain Invariant Single Image Dehazing

TL;DR

This paper introduces a novel encoder-decoder network with spatially aware channel attention and adversarial training to achieve domain-invariant single image dehazing, effectively handling non-uniform haze and diverse datasets.

Contribution

It proposes a new architecture combining attention mechanisms and adversarial training to improve dehazing performance across different haze densities and real-world scenarios.

Findings

Achieves state-of-the-art dehazing results on multiple datasets.

Effectively handles non-uniform haze distributions.

Demonstrates strong domain invariance in diverse environments.

Abstract

Presence of haze in images obscures underlying information, which is undesirable in applications requiring accurate environment information. To recover such an image, a dehazing algorithm should localize and recover affected regions while ensuring consistency between recovered and its neighboring regions. However owing to fixed receptive field of convolutional kernels and non uniform haze distribution, assuring consistency between regions is difficult. In this paper, we utilize an encoder-decoder based network architecture to perform the task of dehazing and integrate an spatially aware channel attention mechanism to enhance features of interest beyond the receptive field of traditional conventional kernels. To ensure performance consistency across diverse range of haze densities, we utilize greedy localized data augmentation mechanism. Synthetic datasets are typically used to ensure a large amount of paired training samples, however the methodology to generate such samples introduces a gap between them and real images while accounting for only uniform haze distribution and overlooking more realistic scenario of non-uniform haze distribution resulting in inferior dehazing performance when evaluated on real datasets. Despite this, the abundance of paired samples within synthetic datasets cannot be ignored. Thus to ensure performance consistency across diverse datasets, we train the proposed network within an adversarial prior-guided framework that relies on a generated image along with its low and high frequency components to determine if properties of dehazed images matches those of ground truth. We preform extensive experiments to validate the dehazing and domain invariance performance of proposed framework across diverse domains and report state-of-the-art (SoTA) results.