Visibility Enhancement for Low-light Hazy Scenarios

TL;DR

This paper introduces a novel framework combining dehazing and enhancement techniques, along with a physically based dataset simulation, to improve visibility in low-light hazy scenes, outperforming existing methods.

Contribution

The paper proposes a cross-consistency dehazing-enhancement framework and a physically based simulation model for low-light hazy images, addressing the limitations of separate dehazing and enhancement methods.

Findings

Outperforms state-of-the-art methods in SSIM and PSNR metrics.

Demonstrates effectiveness through extensive experiments and user studies.

Provides a new dataset with ground-truths for low-light hazy scenarios.

Abstract

Low-light hazy scenes commonly appear at dusk and early morning. The visual enhancement for low-light hazy images is an ill-posed problem. Even though numerous methods have been proposed for image dehazing and low-light enhancement respectively, simply integrating them cannot deliver pleasing results for this particular task. In this paper, we present a novel method to enhance visibility for low-light hazy scenarios. To handle this challenging task, we propose two key techniques, namely cross-consistency dehazing-enhancement framework and physically based simulation for low-light hazy dataset. Specifically, the framework is designed for enhancing visibility of the input image via fully utilizing the clues from different sub-tasks. The simulation is designed for generating the dataset with ground-truths by the proposed low-light hazy imaging model. The extensive experimental results show that the proposed method outperforms the SOTA solutions on different metrics including SSIM (9.19%) and PSNR(5.03%). In addition, we conduct a user study on real images to demonstrate the effectiveness and necessity of the proposed method by human visual perception.