IDRLP: Image Dehazing Using Region Line Prior

Abstract

In this work, a novel and ultra-robust single image dehazing method called IDRLP is proposed. It is observed that when an image is divided into n regions, with each region having a similar scene depth, the brightness of both the hazy image and its haze-free correspondence are positively related with the scene depth. Based on this observation, this work determines that the hazy input and its haze-free correspondence exhibit a quasi-linear relationship after performing this region segmentation, which is named as region line prior (RLP). By combining RLP and the atmospheric scattering model (ASM), a recovery formula (RF) can be easily obtained with only two unknown parameters, i.e., the slope of the linear function and the atmospheric light. A 2-D joint optimization function considering two constraints is then designed to seek the solution of RF. Unlike other comparable works, this "joint optimization" strategy makes efficient use of the information across the entire image, leading to more accurate results with ultra-high robustness. Finally, a guided filter is introduced in RF to eliminate the adverse interference caused by the region segmentation. The proposed RLP and IDRLP are evaluated from various perspectives and compared with related state-of-the-art techniques. Extensive analysis verifies the superiority of IDRLP over state-of-the-art image dehazing techniques in terms of both the recovery quality and efficiency. A software release is available at https://sites.google.com/site/renwenqi888/.

Towards Efficient Single Image Dehazing and Desnowing

“…Prior-based Dehazing Methods. Image dehazing was traditional image processing methods based on physical models when deep learning was not yet popular, which mostly utilized various priors to obtain the prerequisites of dehazing, such as dark channel prior [14], color lines prior [11], haze-lines [3], color attenuation prior [47], region lines prior [18] and non-local prior [2]. The most well-known DCP used the dark channel prior to estimate the transmission map whose principle is based on the assumption that the local patch of the haze-free image is close to zero in the lowest pixel of the three channels.…”

Underwater Images Enhancement by Revised Underwater Images Formation Model

“…Ju et al [29] introduces a light absorption coefficient in the atmospheric scattering model, which resolves the dim effect and better simulates hazy outdoor scenes. Also Ju et al [30] proposed a combination of region line prior and atmospheric scattering model, which effectively utilizes the information of the image to obtain more accurate results. Zhuang et al [31] proposed the Bayesian retinex algorithm for underwater image enhancement by imposing multi-step gradient priors on reflectance and illumination layers.…”

Local Defogging Algorithm for Improving Visual Impact in Image Based on Multiobjective Optimization

“…To remove the noise in the image, an appropriate image filter must be used in conjunction with the objective function. e median filter [13], mean filter [14], Gaussian filter [15], bilateral filter [16], and other image filters are common. ese filters are widely used in image dehazing.…”

“…But this model was built based on a prior assumption like in traditional methods. In [13], a gated fusion defogging network (GFN) was proposed which is built through the sequence of operations such as contrast enhancement, gamma correction, and white balance. But the implementations of these operations were complicated [14].…”