Removing Rain from a Single Image via Discriminative Sparse Coding

By Yu Luo, Yong Xu, Hui Ji. 2015

804 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): “DSC [24] 18.”
Image De-Raining Transformer (2022, background): “Luo et al. [29] proposed a dictionary learning based approach to separate the background layer from the rain-polluted image.”
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].”
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].”
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.”
Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks (2020, methodology): “…removal) with state-of-the-art methods: image decomposition (ID) [12], CNN-based rain drop removal (CNN) [38], discriminative sparse coding (DSC) [15], layer priors (LP) [21], deep detail network (DetailNet) [1], directional global sparse model (UGSM) [63], joint convolutional analysis and…”
Removing Rain from Single Images via a Deep Detail Network (2017, methodology): “third and forth columns, method [25] leaves significant rain streaks and method [24] contains rain artifacts.”
Lightweight Pyramid Networks for Image Deraining (2018, methodology): “A discriminative sparse coding method is proposed in [12].”
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].”
Joint Bi-layer Optimization for Single-Image Rain Streak Removal (2017, methodology): “[21] took a discriminative sparse-coding approach to rain removal by separating sparse codes associated with background patches from codes associated with the patches of the rain image.”
Single Image Deraining using Scale-Aware Multi-Stage Recurrent Network (2017, methodology): “Luo et al’s [16] proposes a discriminative sparse coding framework.”
Learning A Sparse Transformer Network for Effective Image Deraining (2023, methodology): “Since image deraining is an illposed problem, traditional methods [12, 20, 24, 30, 60] usually develop kinds of image priors to provide additional constraints.”
Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining (2018, methodology): “For single image deraining, traditional methods, such as discriminative sparse coding [5], low rank representation [6], and the Gaussian mixture model [7], have been applied to this task and they work quite well.”
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 coding-based method (DSC) [19] (ICCV’15), (b) Gaussian mixture model (GMM) based method [17] (CVPR’16), (c) CNN method (CNN) [5] (TIP’17), (d) Joint Rain Detection and Removal (JORDE”
Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study (2019, methodology): “coding [11], Gaussian mixture model [12], rain direction prior [13], transformed low rank model [14].”
Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning (2019, background): “This applies to all the image-based [16, 24, 14, 22, 38, 7, 40, 21] and video-based works [41, 8, 1, 3, 23, 17, 6, 19, 31, 5, 32, 33, 39].”
Progressive Image Deraining Networks: A Better and Simpler Baseline (2019, methodology): “On the other hand, screen blend model [22, 26] is assumed to be more realistic for the composition of rainy image, based on which Luo et al.”