Removing Rain Streaks by a Linear Model

Abstract

Removing rain streaks from a single image continues to draw attentions today in outdoor vision systems. In this paper, we present an efficient method to remove rain streaks. First, the location map of rain pixels needs to be known as precisely as possible, to which we implement a relatively accurate detection of rain streaks by utilizing two characteristics of rain streaks.The key component of our method is to represent the intensity of each detected rain pixel using a linear model: p = αs+β, where p is the observed intensity of a rain pixel and s represents the intensity of the background (i.e., before rain-affected). To solve α and β for each detected rain pixel, we concentrate on a window centered around it and form an L2-norm cost function by considering all detected rain pixels within the window, where the corresponding rain-removed intensity of each detected rain pixel is estimated by some neighboring non-rain pixels. By minimizing this cost function, we determine α and β so as to construct the final rainremoved pixel intensity. Compared with several state-of-the-art works, our proposed method can remove rain streaks from a single color image much more efficiently -it offers not only a better visual quality but also a speed-up of several times to one degree of magnitude.

A new two‐stage method for single image rain removal

“…In 2018, Hassim et al [7] proposed a hybridization of rain detection and removal technique based on dictionary learning. In 2020, Wang et al [8] first detected the rain locations with some specially designed filters and proposed an effective linear model for rain removal.…”

“…In 2020, Wang et al. [8] first detected the rain locations with some specially designed filters and proposed an effective linear model for rain removal.…”

“…A straightforward method to remove rain from images/ videos is to adopt a two-stage strategy of detection and repair [2][3][4][5][6][7][8]. However, these methods tend to falsely detect non-rain image boundaries that are consistent with the orientation of the rain, and sometimes blur or even damage the non-rain parts.…”

Progressive Rain Removal via a Recurrent Convolutional Network for Real Rain Videos

“…Although the removal of rain, haze and snow from images has been extensively studied for years [1]- [9], [49], [50]- [60], it remains challenging because it is an inherently ill-posed problem. Several non-deep-learning-based rain removal methods, such as frequency domain representation [10], Gaussian mixture model [11], and sparse representation [12], have been proposed and demonstrated to lead to significant quality improvements.…”

“…Several non-deep-learning-based rain removal methods, such as frequency domain representation [10], Gaussian mixture model [11], and sparse representation [12], have been proposed and demonstrated to lead to significant quality improvements. Owing to increasing interest in deep learning recently, few deep-learning-based rain removal methods have been proposed [1]- [5], [13]- [14], [27]- [32], [49], [50]- [57]. Deep networks allow us to easily learn the correlation between rain streaks and background and typically achieve better performance than non-deep-learning approaches.…”