Gradual Network for Single Image De-raining

Yu, Weijiang; Huang, Zhe; Zhang, Wayne; Feng, Litong; Xiao, Nong

doi:10.1145/3343031.3350883

Cited by 32 publications

(29 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Firstly, the single-stage network often fails to function well for relatively difficult tasks due to its limited mapping capability. More recently, the literature [10,11,12] has revealed the advantage of multi-stage training over single-stage methods in many tasks, e.g., image deraining and speech separation. Secondly, due to the nonlinear characteristics of DNNs, some nonlinear distortion may be introduced when the test set mismatches the training conditions.…”

Section: Introductionmentioning

confidence: 99%

ICASSP 2021 Deep Noise Suppression Challenge: Decoupling Magnitude and Phase Optimization with a Two-Stage Deep Network

Liu

Luo

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

It remains a tough challenge to recover the speech signals contaminated by various noises under real acoustic environments. To this end, we propose a novel system for denoising in the complicated applications, which is mainly comprised of two pipelines, namely a two-stage network and a post-processing module. The first pipeline is proposed to decouple the optimization problem w.r.t. magnitude and phase, i.e., only the magnitude is estimated in the first stage and both of them are further refined in the second stage. The second pipeline aims to further suppress the remaining unnatural distorted noise, which is demonstrated to sufficiently improve the subjective quality. In the ICASSP 2021 Deep Noise Suppression (DNS) Challenge, our submitted system ranked top-1 for the real-time track 1 in terms of Mean Opinion Score (MOS) with ITU-T P.808 framework.

show abstract

Section: Introductionmentioning

confidence: 99%

ICASSP 2021 Deep Noise Suppression Challenge: Decoupling Magnitude and Phase Optimization with a Two-Stage Deep Network

Liu

Luo

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…where O denotes a rain image, which can be decomposed into a rain streak component S and a clean background B. RSM is widely employed in data-driven SID methods, such as [22,23,27,50,51,52]. Datasets like Rain800, Rain14000, and Rain12000 are synthesized based on this model.…”

Section: Synthetical Rain Modelmentioning

confidence: 99%

“…Where the term "network" indicates that whether this deraining method can learn all the information in their rain models. [24] specific RAM black-box Qian et al [26] general RMM black-box PReNet [25] specific RRM black-box SPANet [27] general RSM black-box JORDER [19] specific RAM black-box Wang et al [40] specific TTM white-box MSPFN [50] specific RSM white-box JDNet [51] specific RSM white-box GraNet [52] specific RSM white-box Fu et al [18] general RRM white-box MPRNet [56] specific RRM white-box Fu et al [55] specific RRM white-box RCDNet [59] specific RCD white-box DDC-Net [41] specific SBM white-box…”

Section: Solving Paradigms Of Sidmentioning

confidence: 99%

“…(5)) and neglect to predict the transmission maps and atmospheric light in their network architecture, while [20,22,25,26,27] cannot to predict rain streak information; 2) the training data are not consistent with the rain models. For example, the methods in [50,51,52] use RSM (Eqn.…”

Section: Implicit Solving Paradigmmentioning

confidence: 99%

“…MPRNet [50] CCN [34] Semi-DerainGAN [58] CVID [59] RCDNet [53] Pan et al [60] MSPFN [44] RDDAN [61] JDNet [45] QuDeC [62] Syn2Real [ [70] GraNet [46] LPNet [71] PReNet [31] DAF-Net [22] ReHEN [72] DDC-Net [35] RR-GAN [73] MH-DerainNet [74] SIRR [75] SPANet [33] ReMAEN [76] UD-GAN [77] UMRL [78] ID-CGAN [32] Li et al [23] JORDER-E [56] JORDER [21] RWL [79] DualCNN [80] NLEDN [81] RESCAN [55] ResGuideNet [82] Qian et al [25] DID-MDN [24] Li et al [83] DerainNet [83] Fu et al [20] Quan et al [52] SSDRNet [67] MOEDN [56] RICNet [35] JRGR [57] RLNet [59] QSMD [58] Fig. 7: The division of recent SID methods from six aspects based on the three factors.…”

Section: Synthetical Mathematical General Specificmentioning

confidence: 99%

See 2 more Smart Citations

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

Zhang¹,

Yue²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

<div>Abstract—Due to the powerful fitting ability of neural networks and massive training data, data-driven Single Image Deraining (SID) methods have obtained significant performance, and most of the existing studies focus on improving the deraining performance by proposing different kinds of deraining networks. However, the generalization ability of current SID methods may still be limited in the real scenario, and the deraining results also cannot effectively improve the performance of subsequent high-level tasks (such as object detection). The main reason may be because the current works mainly focus on designing new deraining neural networks, while neglecting the interpretation of the solving process. To investigate these issues, we in this paper re-examine the three important factors (i.e.,data, rain model and network architecture) for the SID task, 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 will also study the relationship of the three factors from new perspectives of data, and reveal two different solving paradigms (explicit vs. implicit) for the SID task. Besides, we also profoundly studied one of the three factors, i.e., data, and measured the performance of current methods on different datasets via extensive experiments to reveal the effectiveness of SID data. Finally, with the above comprehensive review and in-depth analysis, we also draw some valuable conclusions and suggestions for future research.</div>

show abstract