computer-vision-11

Single Image Deraining

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in single-image-deraining-11

Trend

Dataset

Best Model

Actions

Rain100L

Rain100H

Test1200

Libraries

i

Use these libraries to find single-image-deraining-11 models and implementations

swz30/MPRNet

2 papers 1,092

Datasets

Raindrop

Synthetic Rain Datasets

RainCityscapes

Real Rain Dataset

Subtasks

No subtasks available.

Most implemented papers

Pre-Trained Image Processing Transformer

Yunhe Wang, Hanting Chen, Zhenhua Liu, Chunjing Xu, Siwei Ma, Wen Gao, Tianyu Guo, Yiping Deng, Chao Xu•Mon Nov 30 2020

To maximally excavate the capability of transformer, the IPT model is presented to utilize the well-known ImageNet benchmark for generating a large amount of corrupted image pairs and the contrastive learning is introduced for well adapting to different image processing tasks.

1992

Content

Test100

Test2800

RainCityscapes

Raindrop

Rain1400

Rain12

swz30/MIRNet

2 papers 622

swz30/CycleISP

2 papers 469

swz30/mirnetv2

2 papers 364

0

Paper Graph

Restormer: Efficient Transformer for High-Resolution Image Restoration

Salman Hameed Khan, Munawar Hayat, Ming-Hsuan Yang, Syed Waqas Zamir, F. Khan, Aditya Arora•Wed Nov 17 2021

This work proposes an efficient Transformer model by making several key designs in the building blocks (multi-head attention and feed-forward network) such that it can capture long-range pixel interactions, while still remaining applicable to large images.

3334 0

Paper Graph

Multi-Stage Progressive Image Restoration

Ling Shao, Salman Hameed Khan, Munawar Hayat, Syed Waqas Zamir, F. Khan, Ming-Hsuan Yang, Aditya Arora•Wed Feb 03 2021

This paper proposes a novel synergistic design that can optimally balance these competing goals in image restoration tasks, that progressively learns restoration functions for the degraded inputs, thereby breaking down the overall recovery process into more manageable steps.

1950 0

Paper Graph

NASNet: A Neuron Attention Stage-by-Stage Net for Single Image Deraining

Zhiling Wang, Xu Qin•Thu Dec 05 2019

This paper proposes a novel end-to-end Neuron Attention Stage-by-Stage Net (NASNet), which can solve all types of rain model tasks efficiently and significantly outperforms the state-of-theart methods by a large margin in terms of both quantitative and qualitative measures.

47 0

Paper Graph

Multi-Scale Progressive Fusion Network for Single Image Deraining

Kui Jiang, Zhongyuan Wang, Peng Yi, Chen Chen, Baojin Huang, Yimin Luo, Jiayi Ma, Junjun Jiang•Mon Mar 23 2020

This work explores the multi-scale collaborative representation for rain streaks from the perspective of input image scales and hierarchical deep features in a unified framework, termed multi- scale progressive fusion network (MSPFN) for single image rain streak removal.

757 0

Paper Graph

Progressive Image Deraining Networks: A Better and Simpler Baseline

Deyu Meng, W. Zuo, Peng Fei Zhu, Q. Hu, Dongwei Ren•Fri Jan 25 2019

A better and simpler baseline deraining network by considering network architecture, input and output, and loss functions is provided and is expected to serve as a suitable baseline in future deraining research.

947 0

Paper Graph

Spatial Attentive Single-Image Deraining With a High Quality Real Rain Dataset

Rynson W. H. Lau, Ke Xu, Tianyu Wang, Xin Yang, Shaozhe Chen, Qiang Zhang•Mon Apr 01 2019

A semi-automatic method that incorporates temporal priors and human supervision to generate a high-quality clean image from each input sequence of real rain images is proposed, and a novel SPatial Attentive Network (SPANet) is proposed to remove rain streaks in a local-to-global manner.

621 0

Paper Graph

SDNet: mutil-branch for single image deraining using swin

Fuxiang Tan, Yuting Kong, Yingying Fan, Feng Liu, Daxin Zhou, Hao Zhang, Long Chen, Liang Gao, Yurong Qian•Sun May 30 2021

Improve the basic module of Swin-transformer and design a three-branch model to implement single-image rain removal and show that the proposed method has performance and inference speed advantages over the current mainstream single- image rain streaks removal models.

18 0

Paper Graph

Clearing the Skies: A Deep Network Architecture for Single-Image Rain Removal

Xueyang Fu, Jiabin Huang, Xinghao Ding, Yinghao Liao, J. Paisley•Tue Sep 06 2016

This work introduces a deep network architecture called DerainNet for removing rain streaks from an image based on the deep convolutional neural network (CNN), which directly learns the mapping relationship between rainy and clean image detail layers from data.

870 0

Paper Graph

EfficientDeRain: Learning Pixel-wise Dilation Filtering for High-Efficiency Single-Image Deraining

Yang Liu, Qing Guo, Wei Feng, Jingyang Sun, Felix Juefei-Xu, L. Ma, Xiaofei Xie•Fri Sep 18 2020

A model-free deraining method, i.e., EfficientDeRain, is proposed, which is able to process a rainy image within 10 ms, over 80 times faster than the state-of-the-art method (i.e. RCDNet), while achieving similar de-rain effects.

111 0

Paper Graph

Adding a benchmark result helps the community track progress.