Joint Bi-layer Optimization for Single-Image Rain Streak Removal

By Lei Zhu, Chi-Wing Fu, Dani Lischinski, P. Heng. IEEE International Conference on Computer Vision, 2017

333 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/b5718e1b87a0e4784640a60ba517c63476c45b7e

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 Transformer (2022, methodology): “Assisted by two priors on the background layer and one prior on the rain layer, Zhu [30] introduced a joint optimization process that alternates between removing rain streaks from the background layer and removing non-rain details from the rain layer.”
Density-Aware Single Image De-raining Using a Multi-stream Dense Network (2018, methodology): “The proposed DID-MDN method is compared with the following recent state-of-the-art methods: (a) Discriminative sparse codingbased method (DSC) [21] (ICCV’15), (b) Gaussian mixture model (GMM) based method [19] (CVPR’16), (c) CNN method (CNN) [6] (TIP’17), (d) Joint Rain Detection and Removal (JORDER”
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.”
A Model-Driven Deep Neural Network for Single Image Rain Removal (2020, background): “Later, researchers made more focus on exploring the prior knowledge of rain and rain-free layers of a rainy image, and designing proper regularizer to extract and separate them [22, 38, 51, 28, 42, 56].”
Lightweight Pyramid Networks for Image Deraining (2018, methodology): “Other methods utilize mixture models [14] and local gradients [15] to model and then remove rain streaks.”
All in One Bad Weather Removal Using Architectural Search (2020, background): “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].”
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.”
Image De-Raining Using a Conditional Generative Adversarial Network (2017, methodology): “In such cases, previous works have designed appropriate prior in solving (1) such as sparsity prior [10]– [13], Gaussian Mixture Model (GMM) prior [14] and patchrank prior [15].”
Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning (2019, neutral): “[16, 14, 41, 7, 38, 22, 36, 43, 23, 6, 29, 21]).”
Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining (2018, background): “[24] combine three different kinds of image priors.”
Depth-Attentional Features for Single-Image Rain Removal (2019, methodology): “Table 2 shows the comparison results with the state-of-the-art rain removal methods, s.t. DID-MDN [50], RESCAN [30], JOB [52], GMMLP [31], and DSC [32].”
Single Image Deraining: A Comprehensive Benchmark Analysis (2019, methodology): “[26] introduced a rain removal method based on the prior that rain streaks typically span a narrow range of directions.”
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”
Semi-Supervised Transfer Learning for Image Rain Removal (2018, methodology): “The visual (e) CNN [10] (f) JORDER [29] (g) JBO [33] (h) Ours effect of derained images verify that our method can remove more rain streaks and better keep the visual quality.”
Cooperative Semantic Segmentation and Image Restoration in Adverse Environmental Conditions (2019, neutral): “Table 3 shows the comparison results with the state- of-the-art rain removal methods, i.e., DSC [26], GMMLP [22], JOB [54], RESCAN [20], DID-MDN [49], SPANet [41], PReNet [32] and DAF-Net [14].”
Gated Context Aggregation Network for Image Dehazing and Deraining (2018, methodology): “Speciﬁcally, we leverage the training dataset synthesized in [43], and compare our method with seven different image deraining meth-ods: DSC [28], GMM [26], CNN [13], JORDER [40], DDN [14], JBO [45] and DID-MDN [43].”