Automatic Single-Image-Based Rain Streaks Removal via Image Decomposition

By Li-Wei Kang, Chia-Wen Lin, Yu-Hsiang Fu. IEEE Transactions on Image Processing, 2012

893 citations recorded by the source corpus.

Rain removal from a video is a challenging problem and has been recently investigated extensively. Nevertheless, the problem of rain removal from a single image was rarely studied in the literature, where no temporal information among successive images can be exploited, making the problem very challenging. In this paper, we propose a single-image-based rain removal framework via properly formulating rain removal as an image decomposition problem based on morphological component analysis. Instead of directly applying a conventional image decomposition technique, the proposed method first decomposes an image into the low- and high-frequency (HF) parts using a bilateral filter. The HF part is then decomposed into a “rain component” and a “nonrain component” by performing dictionary learning and sparse coding. As a result, the rain component can be successfully removed from the image while preserving most original image details. Experimental results demonstrate the efficacy of the proposed algorithm.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7dced2b91599b7dff946a13b007d2e43a0647b8c

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

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”
DesnowNet: Context-Aware Deep Network for Snow Removal (2017, background): “Moreover, rain removal techniques aim to model the general characteristics such as edge orientation [7, 21, 24], shapes [27] or patterns [23] to detect and remove rain particles.”
Single Image Deraining using Scale-Aware Multi-Stage Recurrent Network (2017, methodology): “Fu et al’s [5] is a deep convolutional network that is based on Kang et al’s idea [11].”
Lightweight Pyramid Networks for Image Deraining (2018, background): “[10] decompose a rainy image into its low- and high-”
Clearing the Skies: A Deep Network Architecture for Single-Image Rain Removal (2016, methodology): “This is because most existing methods [9]–[11], [13] only separate rain streaks from object details by using low level features, for example by learning a dictionary to for object representation.”
Multi-Scale Progressive Fusion Network for Single Image Deraining (2020, methodology): “Previous traditional methods for single image derain-ing [5, 14] fail under the complex rain conditions and produce degraded image contents due to the limited linear-mapping transformation.”
Semi-Supervised Transfer Learning for Image Rain Removal (2018, methodology): “An effective rain removal technique can often help an image/video better deliver more accurate detection or recognition results [17].”
Learning A Sparse Transformer Network for Effective Image Deraining (2023, background): “To solve this problem, early approaches [20, 24, 60] usually impose various priors based on statistical properties of rain streaks and clear images.”
Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning (2019, methodology): “[16, 14, 41, 7, 38, 22, 36, 43, 23, 6, 29, 21]).”
Deep Joint Rain Detection and Removal from a Single Image (2016, methodology): “Others focus on rain removal from the single image, by regarding the rain streak removal problem as a signal separation problem [23, 18, 33, 9, 28], or by relying on nonlocal mean smoothing [24].”
Single Image Deraining: A Comprehensive Benchmark Analysis (2019, background): “[2] decomposed an input image into its low and high frequency components.”
Progressive Image Deraining Networks: A Better and Simpler Baseline (2019, background): “Rain is a common weather condition, and has severe adverse effect on not only human visual perception but also the performance of various high level vision tasks such as image classification, object detection, and video surveillance [7,14].”
Image De-raining via Continual Learning (2021, background): “object detection, image classification, person identification, and more [20, 12, 4, 24, 19, 31, 34].”
Removing Rain from Single Images via a Deep Detail Network (2017, methodology): “Several methods using patch-based modeling have also been proposed and represent the current state-of-the-art [5, 14, 15, 18, 24, 25, 31].”
TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions (2021, background): “Adverse weather removal problems like deraining [16, 21,25,51,61,65,76], dehazing [1,2,10,22,42,69], desnowing [29,44,44,73] and rain drop removal [37,39,40,66] have been extensively explored in the literature.”
All in One Bad Weather Removal Using Architectural Search (2020, methodology): “This is also true for bad weather restoration or image enhancement, such as dehazing [47, 3, 1, 57, 7, 13, 26, 43], removal of raindrop and dirt [20, 18, 59, 8, 53, 30, 50, 62, 36, 4], of moderate rain [44, 29], and of heavy rain [25, 54].”
Spatial Attentive Single-Image Deraining With a High Quality Real Rain Dataset (2019, methodology): “In the last decade, we have witnessed a continuous progress on rain removal research with many methods proposed [20, 29, 26, 5, 47, 9], through carefully modeling”