A Generalized Low-Rank Appearance Model for Spatio-temporally Correlated Rain Streaks

By Yi-Lei Chen, Chiou-Ting Hsu. IEEE International Conference on Computer Vision, 2013

440 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/d61fadf436e4163dd99d73a28ad478c7c93973f2

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

In Media Technology

Citations in the corpus

Image De-Raining Using a Conditional Generative Adversarial Network (2017, methodology): “Input PRM [15] DSC [11] CNN [17] GMM [14]”
Single Image Deraining: A Comprehensive Benchmark Analysis (2019, background): “Chen and Hsu [3] decomposed the background and rain streak layers based on low-rank priors.”
Uncertainty Guided Multi-Scale Residual Learning-Using a Cycle Spinning CNN for Single Image De-Raining (2019, background): “Priors such as sparsity [33, 21] and low-rank representation [4] have been used in the literature.”
Multi-Scale Progressive Fusion Network for Single Image Deraining (2020, methodology): “Previous traditional methods for single image deraining [5, 14] fail under the complex rain conditions and produce degraded image contents due to the limited linearmapping transformation.”
Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks (2020, methodology): “In [11], a generalized low rank model is proposed, where the rain streak layer is assumed to be low rank.”
Removing Rain from Single Images via a Deep Detail Network (2017, background): “In [6], the authors propose a generalized model in which additive rain is assumed to be low rank.”
Clearing the Skies: A Deep Network Architecture for Single-Image Rain Removal (2016, methodology): “Method [7] does clearly improve the rainy image, but the proposed method is subjectively superior to all images.”
Joint Bi-layer Optimization for Single-Image Rain Streak Removal (2017, methodology): “, dictionary-based sparse prior [15, 26, 14, 21], low-rank prior [5], nonlocal self-similarity prior [16], and GMM-based layer prior [19].”
Single Image Deraining using Scale-Aware Multi-Stage Recurrent Network (2017, methodology): “Early rain streak removal methods like [14][3] use hand-crafted features or data-driven features for the priors of B and R i .”
Image De-Raining Transformer (2022, methodology): “Chen et al. [9] designed a low-rank model to describe self-similar patterns of rain streaks and remove them from image scenes.”
Rain Streak Removal Using Layer Priors (2016, methodology): “Unlike existing methods in single-image rain streak removal ([2, 11]), our method is easy to implement and generates considerably better results qualitatively and quantitatively.”
Density-Aware Single Image De-raining Using a Multi-stream Dense Network (2018, methodology): “These include sparse coding-based methods [16, 11, 47], lowrank representation-based methods [3, 39] and GMM-based (gaussian mixture model) methods [19].”
A Model-Driven Deep Neural Network for Single Image Rain Removal (2020, background): “, similarity and repeatability of rain streaks [4], low-rankness among multiframes [20], and sparsity and smoothness of rain streaks [18].”
Lightweight Pyramid Networks for Image Deraining (2018, methodology): “Other methods focus on deraining in the Fourier domain [2], using Gaussian mixture models (GMMs) [3], low-rank approximations [4], and via matrix completions [5].”
Depth-Attentional Features for Single-Image Rain Removal (2019, methodology): “In the literature on single-image rain removal, existing methods focused on removing the rain streaks by adopting various image priors [5, 19, 22, 23, 31, 32, 41, 52], or by exploiting a deep convolutional neural network (CNN) to learn a mapping between the training images with and without rain stre”
Semi-Supervised Transfer Learning for Image Rain Removal (2018, methodology): “In recently years, low-rankness [6, 27], total variation [16], stochastic distribution priors [28], convolutional sparse coding [22], neural networks [25] have been applied to the task and achieved satisfying results.”
Progressive Image Deraining Networks: A Better and Simpler Baseline (2019, methodology): “Among these methods, Gaussian mixture model (GMM) [21], sparse representation [35], and low rank representation [1] have been adopted for modeling background image or rain layers.”