Semi-Deraingan: A New Semi-Supervised Single Image Deraining

Wei, Yanyan; Zhang, Zhao; Wang, Yang; Zhang, Haijun; Zhao, Mingbo; Xu, Mingliang; Wang, Meng

doi:10.1109/icme51207.2021.9428285

Cited by 35 publications

(16 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we compare Cycle‐Derain with DisoGAN [30], DualGAN [31], Semi‐DerainGAN[32] and CoGAN [33]. DiscoGAN and DualGAN have the similar architectures in image processing, while their losses are quite different: DiscoGAN adopts a standard GAN loss [30], and DualGAN adopts a Wasserstein GAN loss [31].…”

Section: Experiments and Discussionmentioning

confidence: 99%

An unsupervised generative adversarial network for single image deraining

Song

Guo

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

As the basis of image processing, single image deraining has always been a significant and challenging issue. Due to the lack of real rainy images and corresponding clean images, most deraining networks are trained by synthetic datasets, which makes the output images unsatisfactory in real applications. Besides, note that a heavy rainfall is typically accompanied with some fog. Although some deraining networks have been proposed to remove the rain streaks in the rainy images, the output images may still be blurred due to the accompanied fog. In this paper, these problems existing in single image deraining is comprehensively considered, and propose a Cycle-Derain network based on an unsupervised attention-guided mechanism. Specifically, the Cycle-Derain network takes advantage of generative adversarial networks with two mappings and the cycle consistency loss to train both unpaired rainy images and rain-free images. Moreover, it introduces an unsupervised attention-guided mechanism and exploits the loop-search positioning algorithm to deal with the details of rain and fog in images. Extensive experiments have been carried out, and the results show that the proposed Cycle-Derain network is preferable compared with other deraining networks, especially in term of rainy image restoration.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Experiments and Discussionmentioning

confidence: 99%

An unsupervised generative adversarial network for single image deraining

Song

Guo

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Model optimization-based SID methods include sparse coding [26,75], [9,12] and gaussian mixture model [66]. According to different training modes, data-driven methods can be further divided into fully-supervised deep methods [42,110,136], unsupervised deep methods [53,158] and semi-supervised deep methods [121,124]. Since 2017, the study on SID has entered the deep learning period and has achieved significant performance improvements.…”

Section: Single Image Derainingmentioning

confidence: 99%

Data-Driven Single Image Deraining: A Comprehensive Review and New Perspectives

Zhang¹,

Yue²,

Zhang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Single Image Deraining task aims at recovering the rain-free background from an image degraded by rain streaks and rain accumulation. For the powerful fitting ability of deep neural networks and massive training data, data-driven deep SID methods obtained significant improvement over traditional ones. Current SID methods usually focus on improving the deraining performance by proposing different kinds of deraining networks, while neglecting the interpretation of the solving process. As a result, the generalization ability may still be limited in real-world scenarios, and the deraining results also cannot effectively improve the performance of subsequent high-level tasks (e.g., object detection). To explore these issues, we in this paper re-examine the three important factors (i.e., data, rain model and network architecture) for the SID problem, and specifically analyze them by proposing new and more reasonable criteria (i.e., general vs. specific,synthetical vs. mathematical, black-box vs. white-box). We also study the relationship of the three factors from a new perspective of data, and reveal two different solving paradigms (explicit vs. implicit) for the SID task. We further discuss the current mainstream data-driven SID methods from five aspects, i.e., training strategy, network pipeline, domain knowledge, data preprocessing, and objective function, and some useful conclusions are summarized by statistics. Besides, we profoundly studied one of the three factors, i.e., data, and measured the performance of current methods on different datasets through extensive experiments to reveal the effectiveness of SID data. Finally, with the comprehensive review and in-depth analysis, we draw some valuable conclusions and suggestions for future research.

show abstract

“…Real-world Datasets: For unlabeled real-world images, we build a new real-world rainy dataset called Real200, which contains 400 real-world rainy images (200 training images and 200 testing images) from [16], [28]- [31] and Google search with "real rainy image". Since Semi-DRDNet and some compared approaches are trained in a semi-supervised manner, following the protocols of [3], [48], [49], we train them on three synthetic datasets (Rain200H, Rain200L, and Rain800) as labeled data and Real200 as unlabeled data, which are denoted by &, such as Rain200H&Real200, Rain200L&Real200, and Rain800&Real200.…”

Section: Datasetmentioning

confidence: 99%

Detail-recovery Image Deraining via Dual Sample-augmented Contrastive Learning

Yan¹,

Deng²,

Yang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The intricacy of rainy image contents often leads cutting-edge deraining models to image degradation including remnant rain, wrongly-removed details, and distorted appearance. Such degradation is further exacerbated when applying the models trained on synthetic data to real-world rainy images. We raise an intriguing question -if leveraging both accessible unpaired clean/rainy yet real-world images and additional detail repair guidance, can improve the generalization ability of a deraining model? To answer it, we propose a semi-supervised detail-recovery image deraining network (termed as Semi-DRDNet). Semi-DRDNet consists of three branches: 1) for removing rain streaks without remnants, we present a squeeze-and-excitation (SE)-based rain residual network; 2) for encouraging the lost details to return, we construct a structure detail context aggregation (SDCAB)-based detail repair network; to our knowledge, this is the first time; and 3) for bridging the domain gap, we develop a novel contrastive regularization network to learn from unpaired positive (clean) and negative (rainy) yet real-world images. As a semi-supervised learning paradigm, Semi-DRDNet operates smoothly on both synthetic and real-world rainy data in terms of deraining robustness and detail accuracy. Comparisons on four datasets show clear visual and numerical improvements of our Semi-DRDNet over thirteen state-of-the-arts. Code is available at https://github.com/Dengsgithub/DRD-Net.

show abstract

Semi-Deraingan: A New Semi-Supervised Single Image Deraining

Cited by 35 publications

References 18 publications

An unsupervised generative adversarial network for single image deraining

An unsupervised generative adversarial network for single image deraining

Data-Driven Single Image Deraining: A Comprehensive Review and New Perspectives

Detail-recovery Image Deraining via Dual Sample-augmented Contrastive Learning

Contact Info

Product

Resources

About