Single Image Haze Removal Based on Priori Image Geometry and Edge-Preserving Filtering

Images captured in foggy weather conditions often suffer from bad visibility. Therefore, in this paper, we propose an efficient and automatic method to remove hazes from a single input image. Our method benefits much from an exploration on the priori image geometry on the transmission function. This prior, combined with an edge-preserving texture-smoothing filtering, is applied to estimate the unknown transmission map. Next, the restored image is obtained by taking the estimated transmission map and the atmospheric light into the image degradation model to recover the scene radiance. The proposed method is controlled by just a few parameters and can restore a high-quality haze-free image with fine image details. The experimental results demonstrate that our method shows competitive performance against other methods.