LVRNet: Lightweight Image Restoration for Aerial Images under Low Visibility
This addresses the need for efficient image restoration in autonomous surveillance under poor conditions, though it is incremental with a new dataset and lightweight model.
The paper tackles the problem of restoring clear images from aerial images degraded by multiple low-visibility factors like haze and low light, introducing LVRNet and a new dataset, achieving a PSNR of 25.744 and SSIM of 0.905 with low latency.
Learning to recover clear images from images having a combination of degrading factors is a challenging task. That being said, autonomous surveillance in low visibility conditions caused by high pollution/smoke, poor air quality index, low light, atmospheric scattering, and haze during a blizzard becomes even more important to prevent accidents. It is thus crucial to form a solution that can result in a high-quality image and is efficient enough to be deployed for everyday use. However, the lack of proper datasets available to tackle this task limits the performance of the previous methods proposed. To this end, we generate the LowVis-AFO dataset, containing 3647 paired dark-hazy and clear images. We also introduce a lightweight deep learning model called Low-Visibility Restoration Network (LVRNet). It outperforms previous image restoration methods with low latency, achieving a PSNR value of 25.744 and an SSIM of 0.905, making our approach scalable and ready for practical use. The code and data can be found at https://github.com/Achleshwar/LVRNet.