Removing Rain from Single Images via a Deep Detail Network

By Xueyang Fu, Jiabin Huang, Delu Zeng, Yue Huang, Xinghao Ding, John William Paisley. 2017

1,228 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

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

Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising (2019, neutral): “7297 DetailsNet [7] 21.”
Pre-Trained Image Processing Transformer (2020, methodology): “Input DSC [28] GMM [49] JCAS [31] Clear [27] DDN [ demonstrates that the pre-trained model can capture more useful information and features from the large-scale dataset.”
Deep Generalized Unfolding Networks for Image Restoration (2022, methodology): “Specifically, we use 11,200 clean-rain image pairs in Rain14000 [20], 1,800 image pairs in Rain1800 [71], 700 image pairs in Rain800 [82] and 12”
MAXIM: Multi-Axis MLP for Image Processing (2022, methodology): “Evaluation was performed on five test sets, Rain100H [102], Rain100L [102], Test100 [112], Test1200 [111], and Test2800 [26].”
Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study (2019, methodology): “We employ five state-of-the-art deep learning-based deraining algorithms: (a) JOint Rain DEtection and Removal19 (JORDER) [17]; (b) Deep Detail Network20 (DDN) [15]; (c) Conditional Generative Adversarial Network21 (CGAN) [63]; (d) Density-aware Image De-raining method using a Multistream Dense Netw”
Restoring Vision in Adverse Weather Conditions With Patch-Based Denoising Diffusion Models (2022, methodology): “deep detail network [2], [41], and the joint rain detection and removal (JORDER) method [42].”
Joint Bi-layer Optimization for Single-Image Rain Streak Removal (2017, methodology): “[10], we find that these methods generally improve upon previous works, but still retain some rain streaks in the results; see Fig.”
Learning to Remove Rain in Traffic Surveillance by using Synthetic Data (2019, methodology): “Fu et al. (2017a) combined a guided filter with a three-layer CNN to produce rain-free images.”
Progressive Image Deraining Networks: A Better and Simpler Baseline (2019, methodology): “Rainy image DDN [6] PRN PReNet Figure 7.”
Density-Aware Single Image De-raining Using a Multi-stream Dense Network (2018, methodology): “Even though there exist several large-scale synthetic datasets [7, 41, 36], they lack the availability of the corresponding rain-density label information for each synthetic rainy image.”
DesnowNet: Context-Aware Deep Network for Snow Removal (2017, background): “In the design of [20] and [21], they first separate a rainy image into a high frequency detail layer and a low frequency base layer, under the assumption that they possess and are devoid of rain particles, respectively.”
Multi-Scale Progressive Fusion Network for Single Image Deraining (2020, methodology): “To this end, we collect about 13700 clean/rain image pairs from [41, 7] for training our network as well as other competing methods for a fair comparison.”
CLEARER: Multi-Scale Neural Architecture Search for Image Restoration (2020, methodology): “From the left to the right are Input, DSC [26], LP [18], DetailsNet [6], JORDER [45], SCAN [17], RESCAN [17], CLEARER, and Ground truth.”
All in One Bad Weather Removal Using Architectural Search (2020, methodology): “Metric DetailsNet [8] DesnowNet [38] Ours PSNR 19.”
MSR-net: Low-light Image Enhancement Using Deep Convolutional Network (2017, background): “[9] try to remove rain from single images via a deep detail network.”
Visual Quality Enhancement Of Images Under Adverse Weather Conditions (2018, methodology): “Fu et al [10] in their paper show structural similarity on a subset of images from their training data.”
Multi-Stage Progressive Image Restoration (2021, methodology): “With this single trained model, we perform evaluation on various test sets, including Rain100H [79], Rain100L [79], Test100 [87], Test2800 [22], and Test1200 [86].”