Single Image Defogging by Multiscale Depth Fusion

Abstract

Restoration of fog images is important for the deweathering issue in computer vision. The problem is ill-posed and can be regularized within a Bayesian context using a probabilistic fusion model. This paper presents a multiscale depth fusion (MDF) method for defog from a single image. A linear model representing the stochastic residual of nonlinear filtering is first proposed. Multiscale filtering results are probabilistically blended into a fused depth map based on the model. The fusion is formulated as an energy minimization problem that incorporates spatial Markov dependence. An inhomogeneous Laplacian-Markov random field for the multiscale fusion regularized with smoothing and edge-preserving constraints is developed. A nonconvex potential, adaptive truncated Laplacian, is devised to account for spatially variant characteristics such as edge and depth discontinuity. Defog is solved by an alternate optimization algorithm searching for solutions of depth map by minimizing the nonconvex potential in the random field. The MDF method is experimentally verified by real-world fog images including cluttered-depth scene that is challenging for defogging at finer details. The fog-free images are restored with improving contrast and vivid colors but without over-saturation. Quantitative assessment of image quality is applied to compare various defog methods. Experimental results demonstrate that the accurate estimation of depth map by the proposed edge-preserved multiscale fusion should recover high-quality images with sharp details.

Enhanced Variational Image Dehazing

“…The original image in Fig. (4.3a) was extracted from [48]. The sun appears behind the haze at the upper left part of the image, producing a non-uniform illuminant: the leftmost part of the sky appears brighter than the rightmost side.…”

“…Most of these advantages come from the fact [48]. Result of processing with methods of (b) Wang et al method [48]. (c) He et al [17].…”

“…In [1], a multi-scale fusion strategy is adopted, in which the authors compute several weighting maps (based on luminance, chromaticity and saliency), that they use to fuse a white-balanced and a contrast enhanced version of the original degraded image. In [48], the depth map is obtained by a fusion procedure in a probabilistic framework.…”

An Improved Defogging Algorithm Based on Dark Color Theory Combined with Self-Adaptive Threshold Mechanism

“…Currently, most of image defogging algorithms are based on image restoration, the core idea of which is as follows: firstly, an imaging mode should be established; secondly, the degraded part of the imaging model is compensated and the interferential part of it is filtered; thirdly, the clear image is restored [5][6][7][8][9][10][11][12][13][14][15][16][17]. Theoretically, the defogging effect of these algorithms can be ideal; however, most of the existing imaging models are dependent on the image depth information; unfortunately, they cannot be accurately calculated using a single image.…”

Image Dehazing (Defogging) by using Depth Estimation and Fusion with Guided Filter

“…It recognizes the degree of snowfall automatically even in the low visibility by fog. In 2015 Zhao et al [5] removed the fog by Image defogging (IDF) method that influences from the fogs in an image to improve its quality. For the single scattering of light dominated pixels the single scattering physics model is used in the hybrid model and for the remaining pixels the multiple scattering physics model (MSPM) is used.…”