Detection and removal of rain from videos

By K. Garg, Shree K. Nayar. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., 2004

572 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/371616e0e6ffdfdd1690337a9c1d7ed5b6d47766

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks (2020, background): “Rain image recovery [3], [4], [5], [6], [7], [8], [9], [10], [11] from”
Image De-Raining Using a Conditional Generative Adversarial Network (2017, background): “In the case of video-based de-raining, a common strategy to solve (1) is to leverage additional temporal information, such as methods proposed in [6]–[9].”
A Model-Driven Deep Neural Network for Single Image Rain Removal (2020, methodology): “Garg and Nayar [10] ﬁrst tried to analyze the visual effects of raindrops on imaging systems, and utilized a space-time correlation model to capture the dynamics of raindrops and a physics-based motion blur model to illustrate the photometry of rain.”
Blind Haze Separation (2006, background): “Imaging in poor atmospheric conditions [3, 7, 12, 20] affects human activities, as well as remote sensing and surveillance.”
Removing Rain from a Single Image via Discriminative Sparse Coding (2015, background): “[9].”
Restoring an Image Taken through a Window Covered with Dirt or Rain (2013, background): “Garg and Nayar [7] and Barnum et al.”
Depth-Attentional Features for Single-Image Rain Removal (2019, methodology): “Other than images, several methods [10, 38] have been developed to remove rain in videos.”
Semi-Supervised Transfer Learning for Image Rain Removal (2018, background): “Early video derain methods [13, 2, 3, 18] designed many useful techniques to detect potential rain streaks based on their physical characteristics and removed these detected rain by image restoration algorithms.”
Progressive Image Deraining Networks: A Better and Simpler Baseline (2019, methodology): “Based on linear summation model, optimization-based methods have been also extended for video deraining [8,12,13,16,19].”
Removing Rain from Single Images via a Deep Detail Network (2017, methodology): “For video-based methods, rain can be more easily identified and removed using inter-frame information [3,4,10,21, 28, 35].”
Single Image Deraining: A Comprehensive Benchmark Analysis (2019, methodology): “Garg and Nayar [21] proposed a rain streak detection and removal method from a video by taking the average intensity of the detected rain streaks from the previous and subsequent frames.”
Lightweight Pyramid Networks for Image Deraining (2018, background): “The first study on video deraining removed rain from a static background using average intensities from the neighboring frames [1].”
Rain Streak Removal Using Layer Priors (2016, methodology): “Garg and Nayar [5] propose another method that exploits the ability to control a video camera’s operational parameters when capturing a rainy scene.”
Analysis of Rain and Snow in Frequency Space (2008, methodology): “Temporal median filtering is the simplest method for cleaning videos (Hase et al. 1999; Starik and Werman 2003).”
Rain Removal in Traffic Surveillance: Does it Matter? (2018, methodology): “If we look at the average processing times per image listed in Table XI, the method by Garg and Nayar [1] is 38 times faster than the method by Kim et al. [20] and should thus be preferred due to superior speed.”
Deep Joint Rain Detection and Removal from a Single Image (2016, background): “Some focus on rain image recovery from video sequences [3, 4, 5, 9, 13, 14, 15, 16, 44].”
Rain Removal in Video by Combining Temporal and Chromatic Properties (2006, methodology): “Garg and Nayar classified the weather into two types [3]: steady weather such as fog and haze, and dynamic weather such as rain and snow, based on the size of the weather particles.”
Image De-Raining Transformer (2022, background): “To alleviate the impact of rainy artifacts, early researches focus on video de-raining [1], [2], [3], [4], [5], [6], [7] by exploiting the temporal consistency between successive frames as a constraint.”