Joint Bi-layer Optimization for Single-Image Rain Streak Removal
Citations
747 citations
Cites methods from "Joint Bi-layer Optimization for Sin..."
...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]....
[...]
539 citations
Cites background from "Joint Bi-layer Optimization for Sin..."
...[24] combine three different kinds of image priors....
[...]
535 citations
Cites background or methods from "Joint Bi-layer Optimization for Sin..."
...Input DSC [21] (ICCV’15) GMM [19] (CVPR’16) CNN [6] (TIP’17) JORDER [36] (CVPR’17) DDN [7] (CVPR’17) JBO [47] (ICCV’17) DID-MDN Test1 0.7781/21.15 0.7896/21.44 0.8352/22.75 0.8422/22.07 0.8622/24.32 0.8978/ 27.33 0.8522/23.05 0.9087/ 27.95 Test2 0.7695/19.31 0.7825/20.08 0.8105/20.66 0.8289/19.73 0.8405/22.26 0.8851/25.63 0.8356/22.45 0.9092/ 26.0745 Heavy Medium Light Figure 5: Samples synthetic images in three different conditions....
[...]
...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) method [36] (CVPR’17), (e) Deep detailed Network method (DDN) [7] (CVPR’17), and (f) Joint Bi-layer Optimization (JBO) method [47] (ICCV’17)....
[...]
...These include sparse coding-based methods [16, 11, 47], lowrank representation-based methods [3, 39] and GMM-based (gaussian mixture model) methods [19]....
[...]
...Similar results are also observed from [47]....
[...]
...Input DSC [21] (ICCV’15) GMM [19] (CVPR’16) CNN [6] (TIP’17) JORDER [36] (CVPR’17) DDN [7] (CVPR’17) JBO [47] (ICCV’17) DID-MDN...
[...]
387 citations
Cites methods from "Joint Bi-layer Optimization for Sin..."
...Methods Input DSC [29] LP [26] Clear[10] JORDER [40] DDN [11] JBO[47] DID-MDN[42] Our SPANet...
[...]
...[47] exploit rain streak directions to first determine the rain-dominant regions, which are used to guide the process of separating rain streaks from background details based on rain-dominant patch statistics....
[...]
...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...
[...]
344 citations
Cites methods from "Joint Bi-layer Optimization for Sin..."
...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....
[...]
...On the one hand, linear summation is usually adopted as the composition model [1, 21, 35]....
[...]
References
40,609 citations
17,433 citations
"Joint Bi-layer Optimization for Sin..." refers methods in this paper
...Hence, we efficiently solve it by adopting the alternating direction method of multipliers (ADMM) technique [3] by alternatively updating B and α in the following two subproblems (with T iterations):...
[...]
1,624 citations
"Joint Bi-layer Optimization for Sin..." refers methods in this paper
...Second, we explored saliency detection with and without rain using [31]....
[...]
...Here, we randomly selected 30 images from the CSSD dataset [31], added rain to each of them, and then applied our method to remove the rain....
[...]
1,381 citations
"Joint Bi-layer Optimization for Sin..." refers methods in this paper
...Inspired by [9], we use a weighted Laplacian term to formulate Ω(R) with spatially-varying smoothing capability:...
[...]
1,345 citations
"Joint Bi-layer Optimization for Sin..." refers background or methods in this paper
...Dictionary-based sparse prior [23] describes an image patch as a linear combination of a few atoms from a pre-specified dictionary....
[...]
...While a dictionary-based sparse prior has been previously used for rain streak removal [23, 21], Dong et al....
[...]