Single Image Haze Removal Based on a Simple Additive Model With Haze Smoothness Prior

Abstract

Single image haze removal, which is to recover the clear version of a hazy image, is a challenging task in computer vision. In this paper, an additive haze model is proposed to approximate the hazy image formation process. In contrast with the traditional optical model, it regards the haze as an additive layer to a clean image. The model thus avoids estimating the medium transmission rate and the global atmospherical light. In addition, based on a critical observation that haze changes gradually and smoothly across the image, a haze smoothness prior is proposed to constrain this model. This prior assumes that the haze layer is much smoother than the clear image. Benefiting from this prior, we can directly separate the clean image from a single hazy image. Experimental results and comparisons with synthetic images and real-world images demonstrate that the proposed method outperforms state-of-the-art single image haze removal algorithms.

Dark-Channel Soft-Constrained and Object-Perception-Enhanced Deep Dehazing Networks Used for Road Inspection Images

“…To improve the thin cloud interference in remote sensing images, multiscale DCP methods were developed to utilize image dehazing by combining the low-and high-frequency components of the image [7]. In addition, using the smoothing prior to haze, researchers realized single-image dehazing using gradient response filtering of haze [8]. In addition to physical-based methods, empirical-based methods utilize the statistical rule between image features and fog depth for image dehazing.…”