An L0-regularized global anisotropic gradient prior for single-image de-raining

Chen, Huasong; Xu, Zhenhua; Zhang, Yasong; Fan, Yuanyan; Li, Zhenhua

doi:10.1016/j.apm.2021.04.003

Cited by 5 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, researchers have proposed two strategies to solve single image deraining problems: model-based methods and deep learning-based methods. The former often designs priors to model the rain streaks and uses maximum a posterior (MAP) framework to detect the rain streaks and background, such as image multi-component decomposition based methods [3][4], 3-layer hierarchical approach [5], discriminative sparse coding based method [6], Gaussian Mixture Model based method(GMM) [7], directional gradient prior based method [8], and anisotropic global gradient prior based method [9] and so on. Deep learning-based methods use multi-layer convolutional neural networks (CNNs) to learn parameters from training samples and predict the background using the trained networks [10][11][12][13][14][15][16].…”

Section: Introductionmentioning

confidence: 99%

Two-phase single-image deraining method via sparse blind detection and image inpainting

Chen,

Wu,

Liu

et al. 2023

Optoelectronic Imaging and Multimedia Technology X

Self Cite

View full text Add to dashboard Cite

This paper mainly focuses on the rain streak removal task from a single image. Based on the observation that the distribution of rain streak in an image is sparse. We propose a two-phase single image deraining method. Firstly, it detects the rain locations with a proposed anisotropic global gradient prior (AGGP) and generates a rain mask for rain streak removal. Then it recovers the information in rain distorted region with AGGP based multi-layer image inpainting model. Furthermore, to solve the multi-variable optimization problems, we develop an alternating half-quadratic algorithm by introducing alternating algorithm and the variable split method. Both experiments on synthesized and realworld images show the proposed method outperforms state-of-the-art methods in terms of rain streak removal and image multi-layer information preservation.

show abstract