Deep Single Image Deraining via Modeling Haze-Like Effect

Wang, Yinglong; Gong, Daozhi; Yang, Jie; Shi, Qinfeng; Hengel, Anton van den; Xie, Dehua; Zeng, Bing

doi:10.1109/tmm.2020.3013383

Cited by 19 publications

(10 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) Hand-crafted Neural Network-based De-raining Methods: The major development of deep-learning-based deraining methods lies on the manual design of various neural networks [6], [24], [31]- [33], [38], [41], [43], [45], [45]- [47], [53]- [57]. In these de-raining networks, multi-scale architecture [6], [24], [26], [31], [32], [38], [41], [55], [60] and attention module [46], [54], [61] or their combination [33], [45], [56], [57] have been widely incorporated into the design of various image de-raining networks and have achieved the promising performance. The related works are succinctly described as follows: 1) Image de-raining using multi-scale neural networks: Wang et al [55] developed a modeling Haze-Like effect-based deep neural network for image de-raining, in which a SSP module [62] is introduced to extract multiscale features to help remove the haze-like effect.…”

Section: A Image De-raining Methodsmentioning

confidence: 99%

“…Over the past decade, a variety of successful algorithms, ranging from early hand-crafted prior-based methods [19]- [21], [27], [28] to the latest deep learning-based methods [6], [22]- [24], [26], [29]- [39], [41]- [47], [53]- [55], have been proposed to handle the image de-raining task. The priorbased de-raining methods first leverage effective regularizers to characterize the property of the background and rain streak layers, and then separate them by solving an objective function with proper optimization algorithms.…”

mentioning

confidence: 99%

“…For deep learning-based de-raining methods, the major development over the years lies on the design of various effective neural network architectures. Among them, the multi-scale architecture [6], [24], [26], [31], [32], [38], [41], [55] and the attention module [43], [46], [47], [54], [56] or their combination [33], [45], [56], [57] have been demonstrated effective in boosting the performance. Take a few examples, Zhang et al [26] developed a multi-stream densely connected de-raining network to efficiently learn features at different scales.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Multi-scale Attentive Image De-raining Networks via Neural Architecture Search

Liu¹,

Fu²,

Wanliang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Multi-scale architectures and attention modules have shown effectiveness in many deep learning-based image de-raining methods. However, manually designing and integrating these two components into a neural network requires a bulk of labor and extensive expertise. In this article, a high-performance multi-scale attentive neural architecture search (MANAS) framework is technically developed for image deraining. The proposed method formulates a new multi-scale attention search space with multiple flexible modules that are favorite to the image de-raining task. Under the search space, multi-scale attentive cells are built, which are further used to construct a powerful image de-raining network. The internal multiscale attentive architecture of the de-raining network is searched automatically through a gradient-based search algorithm, which avoids the daunting procedure of the manual design to some extent. Moreover, in order to obtain a robust image de-raining model, a practical and effective multi-to-one training strategy is also presented to allow the de-raining network to get sufficient background information from multiple rainy images with the same background scene, and meanwhile, multiple loss functions including external loss, internal loss, architecture regularization loss, and model complexity loss are jointly optimized to achieve robust de-raining performance and controllable model complexity. Extensive experimental results on both synthetic and realistic rainy images, as well as the down-stream vision applications (i.e., objection detection and segmentation) consistently demonstrate the superiority of our proposed method.Index Terms-Image de-raining, multi-scale attentive neural architecture search, multi-to-one training strategy. I. INTRODUCTIONW HEN people take photos in an outdoor environment, the captured images could suffer from visibility degradation owning to various bad weather conditions such as rain [1], [2], haze [3], [4], or snow [5]. Particularly, on a rainy day, the presence of rain can seriously degrade the visual quality of outdoor images, and as a result affects the visual authenticity of human perception and the performance

show abstract

Section: A Image De-raining Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Multi-scale Attentive Image De-raining Networks via Neural Architecture Search

Liu¹,

Fu²,

Wanliang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, deep learning technology drives the development of image restoration tasks [7], [8], [9], [10], [11]. There are lots of learning-based deblurring methods that have been proposed.…”

Section: Introductionmentioning

confidence: 99%

Multi-Scale Grid Network for Image Deblurring With High-Frequency Guidance

Liu

Fang

Wang

et al. 2022

IEEE Trans. Multimedia

View full text Add to dashboard Cite

It has been demonstrated that the blurring process reduces the high-frequency information of the original sharp image, so the main challenge for image deblurring is to reconstruct high-frequency information from the blurry image. In this paper, we propose a novel image deblurring framework to focus on the reconstruction of high-frequency information, which consists of two main subnetworks: a high-frequency reconstruction subnetwork (HFRSN) and a multi-scale grid subnetwork (MSGSN). The HFRSN is built to reconstruct latent high-frequency information from multiple scale blurry images. The MSGSN performs deblurring processes with high-frequency guidance at different scales simultaneously. Besides, in order to better use high-frequency information to restore sharpening images, we designed a high-frequency information aggregation (HFAG) module and a high-frequency information attention (HFAT) module in MSGSN. The HFAG module is designed to fuse high-frequency features and image features at the feature extraction stage, and the HFAT module is built to enhance the feature reconstruction stage. Extensive experiments on different datasets show the effectiveness and efficiency of our method.

show abstract

“…I MAGES captured in rainy condition suffer from quality degradation due to rain streaks and the veiling effect [36] caused by light scattering and water vapor. The degradation severely impacts the performance of computer vision algorithms, including object detection [5], semantic segmentation [13], video surveillance [17], [33] and etc..…”

Section: Introductionmentioning

confidence: 99%

From Heavy Rain Removal to Detail Restoration: A Faster and Better Network

Gao¹,

Wen²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

The dense rain accumulation in heavy rain can significantly wash out images and thus destroy the background details of images. Although existing deep rain removal models lead to improved performance for heavy rain removal, we find that most of them ignore the detail reconstruction accuracy of rain-free images. In this paper, we propose a dual-stage progressive enhancement network (DPENet) to achieve effective deraining with structure-accurate rain-free images. Two main modules are included in our framework, namely a rain streaks removal network (R 2 Net) and a detail reconstruction network (DRNet). The former aims to achieve accurate rain removal, and the latter is designed to recover the details of rain-free images. We introduce two main strategies within our networks to achieve trade-off between the effectiveness of deraining and the detail restoration of rain-free images. Firstly, a dilated dense residual block (DDRB) within the rain streaks removal network is presented to aggregate high/low level features of heavy rain. Secondly, an enhanced residual pixel-wise attention block (ERPAB) within the detail reconstruction network is designed for context information aggregation. We also propose a comprehensive loss function to highlight the marginal and regional accuracy of rainfree images. Extensive experiments on benchmark public datasets show both efficiency and effectiveness of the proposed method in achieving structure-preserving rain-free images for heavy rain removal. The source code and pre-trained models can be found at https://github.com/wybchd/DPENet.

show abstract

Deep Single Image Deraining via Modeling Haze-Like Effect

Cited by 19 publications

References 40 publications

Multi-scale Attentive Image De-raining Networks via Neural Architecture Search

Multi-scale Attentive Image De-raining Networks via Neural Architecture Search

Multi-Scale Grid Network for Image Deblurring With High-Frequency Guidance

From Heavy Rain Removal to Detail Restoration: A Faster and Better Network

Contact Info

Product

Resources

About