Scatter Inpainting Algorithm for Rain or Snow Removal in a Single Image

Hao, Jianyu; Jiang, Murong; Huang, Yaqun; Bai, Yuan; Wang, Yuanhang

doi:10.1109/compcomm.2018.8781043

Cited by 3 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Barunm et al [19] further estimated and eliminated the contrast transformation of the background layer by using contrast enhancement of the background layer and low-pass filtering of the approximate rain line. In order to fully consider and repair damaged raindrop or rain streaks region, Hao et al [6] proposed a method to continuously scan the pixel color value near the seed points with scatter lines, fill the damaged region, repair the image from outside to inside. But this method needs to set the scanning area artificially, when the rain or snow is heavy, the recovery effect is not good, when the raindrops are on the glass, small black spots will appear due to the influence of reflection on the glass.…”

Section: A Model-based Solutionsmentioning

confidence: 99%

“…Some scholars have proposed methods for single image de-raining, which are mainly divided into model-based and deep learning-based methods. For example, the model-based solutions include guided filtering [1], low rank appearance model [2], non-local mean filtering [3], Gaussian mixture model [4], contrast enhancement [5], and scattering repair method [6]. The method based on guided filtering proposed in [1] takes the difference image between the maximum and minimum value of RGB channel of each pixel as the guide image, and the input image is processed by guided filtering to obtain the de-raining image.…”

Section: Introductionmentioning

confidence: 99%

“…Because only one image is used as the guiding image, although it has strong real-time performance, it causes a great loss of details. Paper [6] proposed a scattering repairing method, using scatter lines to scan nearby pixels continuously and filling the damaged rain removal area. But it needs to set the scanning area artificially, and black spots are easy to appear due to the influence of light.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dense Residual Generative Adversarial Network for Rapid Rain Removal

Yuan

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Single-image rain removal always was one of the difficulties in the environment perception task. Usually, it has two paths to solve this problem: data-driven solutions and model-based solutions. Due to the benefits of convenient, learning features automatically and rapidly, data driven solutions has attracted tremendous interests. However, the time consumed per frame is still hard to match the requirement of high real-time performance, especially for high speed unmanned platform. In this article, we propose a fast dense residual generative adversarial network (FDRN), which can remove rain and reduce computation time consumption, the de-raining time of each frame only consumes 0.02s. We enhanced the data of original rainy images, put it into the generator network which is composed of long short-term memory networks (LSTM) and a newly designed dense residual network (DRN). The feature map in generator and discriminator is extracted to calculate the loss function and guide the direction of training. We selected 1500 pairs of synthetic images from existed datasets to train our network. And in order to test our method's de-raining ability realistically, we also selected 147 real-world rainy images from existed datasets. Experiments on both synthetic and real-world rainy images demonstrate that the proposed method can achieve competitive results to some existing methods in performance and effectiveness.INDEX TERMS Rain removal, FDRN, dense residual network, time consuming.

show abstract

Section: A Model-based Solutionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dense Residual Generative Adversarial Network for Rapid Rain Removal

Yuan

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Many scholars have proposed methods for removing raindrops from a single image, which are mainly divided into model-based methods and depth learning methods. For example, model-based guided filtering [1], low rank appearance model [2], nonlocal mean filtering [3], Gaussian mixture model [4], contrast enhancement [5], scattering repair method [6]. For the rain removal of a single image, Kim et al [3] first detected the position of the rain line in the image, and then eliminated the rain line through the nonmean filter.…”

Section: Introductionmentioning

confidence: 99%

“…The disadvantage is that the rain line remains in the image after rain removal, and the image becomes blurred. [6] proposed a scattering restoration method, which uses the pixel values near the scattering line to fill the image area affected by raindrops. However, this method requires manual setting of the area to be scanned.…”

Section: Introductionmentioning

confidence: 99%

MSFSA-GAN: Multi-Scale Fusion Self Attention Generative Adversarial Network for Single Image Deraining

et al. 2022

View full text Add to dashboard Cite

Bad weather such as rainy days will seriously affect the image quality and the accuracy of visual processing algorithm. In order to improve the image deraining quality, a multi-scale fusion self attention generation adversarial network (MSFSA-GAN) is proposed. This network uses different scales to extract input characteristics of rain lines. First, Gaussian pyramid rain maps with different scales are generated by Gaussian algorithm. Then, in order to extract the features of rain lines with different scales, the coarse fusion module and fine fusion module are designed respectively. Next, the extracted features are fused at different scales. In this process, the self attention mechanism is introduced to make the network focus on the extracted features of different scales. And before the fusion, the rain pattern reconstruction operation is also carried out, so that the network can reproduce the input image more perfectly. Finally, it is input into the discriminator network with dense blocks to obtain the image that removes the rain lines. We used R100H and R100L datasets to train and test our network. The results show that our method as high as 27.79 in PSNR and UQI is 0.94, which is superior to the existing methods in performance. Meanwhile, we also compared the cost of time, the result of our network is only 0.02s.INDEX TERMS Rain removal, MSFSA-GAN, self attention, dense block.

show abstract