Rain Streak Removal Using Layer Priors

By Yu Li, Robby T. Tan, Xiaojie Guo, Jiangbo Lu, Michael S. Brown. 2016

912 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising (2019, neutral): “5996 LP [15] 20.”
Pre-Trained Image Processing Transformer (2020, methodology): “Input DSC [28] GMM [49] JCAS [31] Clear [27] DDN [ demonstrates that the pre-trained model can capture more useful information and features from the large-scale dataset.”
Progressive Image Deraining Networks: A Better and Simpler Baseline (2019, methodology): “Five competing methods are considered, including one traditional optimization-based method (GMM [21]) and three state-of-the-art deep CNN-based models, i.”
Clearing the Skies: A Deep Network Architecture for Single-Image Rain Removal (2016, methodology): “As is again evident in these results, method [10] over-smooths the results and methods [11], [13] leave rain streaks, both of which are addressed by our algorithm.”
Single Image Deraining using Scale-Aware Multi-Stage Recurrent Network (2017, methodology): “(1) assume the rain streaks sparse and utilize individual rain streak characteristics (e.g. [14][13]) to separate background and rain streak layers.”
Uncertainty Guided Multi-Scale Residual Learning-Using a Cycle Spinning CNN for Single Image De-Raining (2019, methodology): “On the other hand, single image de-raining methods attempt to use some prior information to remove rain components from a single image [18, 13, 37, 35].”
Image De-Raining Using a Conditional Generative Adversarial Network (2017, methodology): “Input PRM [15] DSC [11] CNN [17] GMM [14]”
Deep Generalized Unfolding Networks for Image Restoration (2022, methodology): “Specifically, we use 11,200 clean-rain image pairs in Rain14000 [20], 1,800 image pairs in Rain1800 [71], 700 image pairs in Rain800 [82] image pairs in Rain12 [39] to train our model.”
Lightweight Pyramid Networks for Image Deraining (2018, methodology): “We compare our LPNet with six state-of-the-art deraining methods: the GMM of [14], a CNN baseline super-resolution convolutional neural network (SRCNN) [25], the deep detail networks (DDNs) of [31], an advanced network called convolution in convolution (CIC) [21], a convolutional neural pyramid (CNP”
Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning (2019, methodology): “’s [22] decomposes the rain image into a rain-free background layer and a rain streak layer, by utilizing Gaussian Mixture Models (GMMs) as a prior for the background and rain streak layers.”
Rain Removal in Traffic Surveillance: Does it Matter? (2018, methodology): “[30], who utilize Gaussian Mixture Models (GMM) to learn two dictionaries of rain and non-rain patterns.”
Image De-Raining Transformer (2022, methodology): “…model-based methods treat this task as a signal separation process and explore various priors about the characteristics of rain streaks, including sparse coding [8], low-rank representations [9], Gaussian mixture model [10], and joint convolutional analysis and synthesis sparse representation [11].”
A Model-Driven Deep Neural Network for Single Image Rain Removal (2020, methodology): “Later, both temporal and chromatic properties of rain were considered and then background layer was extracted from rainy video by utilizing different strategies such as K-means clustering [55], Kalman ﬁlter [33], and GMM [3].”
Density-Aware Single Image De-raining Using a Multi-stream Dense Network (2018, methodology): “Various methods have been proposed in the literature to address this problem [19, 7, 39, 21, 3, 16, 11, 2, 41, 36, 6].”
Joint Bi-layer Optimization for Single-Image Rain Streak Removal (2017, methodology): “A rain image I is often considered as a linear combination of a rain-free background (B) and a rain streak layer (R) [19]:”
Multi-Stage Progressive Image Restoration (2021, methodology): “Datasets Rain14000 [23] Rain1800 [81] Rain800 [90] Rain100H [81] Rain100L [81] Rain1200 [89] Rain12 [48] GoPro [53] HIDE [69] RealBlur [64] SIDD [1] DND [60] Train Samples 11200 1800 700 0 0 0 12 2103 0 0 320 0 Test Samples 2800 0 100 100 100 1200 0 1111 2025 1960 40 50”
Spatial Attentive Single-Image Deraining With a High Quality Real Rain Dataset (2019, methodology): “Methods Input DSC [29] LP [26] Clear[10] JORDER [40] DDN [11] JBO[47] DID-MDN[42] Our SPANet”