Visibility Enhancement for Low-light Hazy Scenarios
This work addresses a specific visual enhancement problem for low-light hazy scenarios, such as those at dusk or early morning, which is incremental as it builds on existing methods for dehazing and low-light enhancement.
The paper tackles the problem of enhancing visibility in low-light hazy images, which is ill-posed and not effectively addressed by existing dehazing and low-light enhancement methods alone. The proposed method outperforms state-of-the-art solutions with improvements of 9.19% in SSIM and 5.03% in PSNR, as validated by experiments and a user study.
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.