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

Zhang, Zhao; Yue, Wei; Zhang, Haijun; Yang, Yi; Yan, Shuicheng; Wang, Meng

doi:10.36227/techrxiv.14944752.v4

Cited by 5 publications

(6 citation statements)

References 138 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our future work will focus on at least two directions. The first is to explore more general image restoration methods, which is not only suitable for image haze removal, but also suitable for image rain removal [29][30][31], image noise removal [32][33][34], etc. The second one is to explore the removal of haze in more complex scenes, such as dense haze scenes [35][36][37] and nightlight haze scenes [38][39][40].…”

Section: Discussionmentioning

confidence: 99%

Black-box Dehazing Network via Joint Loss Function

Zhang,

Zhao,

Song

et al. 2024

Preprint

View full text Add to dashboard Cite

Single image dehazing is a notoriously challenging task in image processing due to the numerous unknown factors involved. Most existing dehazing methods are based on physical models of the haze formation process. However, real-world haze scenes cannot be accurately mathematically modeled due to the existence of various unquantifiable factors in the scene. Therefore, the dehazing methods based on physical models often perform poorly in complex haze scenes. In this paper, we propose a novel black-box dehazing equation. In this equation, the haze is modelled as an additional image interference layer, without explicitly reasoning about the physical model of haze formation. The dehazing process is modelled as removing this image interference layer. Based on this equation, we propose a novel network architecture called the Black-box Dehazing Network (BDN). Moreover, we propose a joint loss function for training this network. The joint loss function not only evaluates pixel-level differences between the dehazed image and the haze-free image, but also measures differences in texture, color, and structure between the hazy image and its corresponding dehazed version as well as those between the hazy image and its haze-free version. In training, BDNet is only fed pairs of haze-free images and their corresponding hazy images. The corresponding hazy patches are generated on-the-fly during network training. Experimental results demonstrate that the proposed method has the advantage of universality and outperforms existing state-of-the-art dehazing methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Black-box Dehazing Network via Joint Loss Function

Zhang,

Zhao,

Song

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Fu et al [29] proposed a biological brain-inspired continual learning algorithm. Zhang et al [30] discussed in this paper the methods to re-examine the three important factors (i.e., data, rain model and network architecture) for the Single Image De-raining (SID) problem and specifically analyse them by proposing new and more reasonable criteria (i.e. general vs. specific, synthetic vs. mathematical, and black-box vs. whitebox).…”

Section: Single Image Rain Removal Methodsmentioning

confidence: 99%

Recursive attention collaboration network for single image de‐raining

Li,

Gong

et al. 2024

IET Cyber-Syst and Robotics

View full text Add to dashboard Cite

Single‐image rain removal is an important problem in the field of computer vision aimed at recovering clean images from rainy images. In recent years, data‐driven convolutional neural network (CNN)‐based rain removal methods have achieved significant results, but most of them cannot fully focus on the contextual information in rain‐containing images, which leads to the failure of recovering some of the background details of the images that have been corrupted due to the aggregation of rain streaks. With the success of Transformer‐based models in the field of computer vision, global features can be easily acquired to better help recover details in the background of an image. However, Transformer‐based models often require a large number of parameters during the training process, which makes the training process very difficult and makes it difficult to apply them to specific devices for execution in reality. The authors propose a Recursive Attention Collaboration Network, which consists of a recursive Swin‐transformer block (STB) and a CNN‐based feature fusion block. The authors designed the Recursively Integrate Transformer Block (RITB), which consists of several STBs recursively connected, that can effectively reduce the number of parameters of the model. The final part of the module can integrate the local information from the STBs. The authors also design the Feature Enhancement Block, which can better recover the details of the background information corrupted by rain streaks of different density shapes through the features passed from the RITB. Experiments show that the proposed network has an effective rain removal effect on both synthetic and real datasets and has fewer model parameters than other mainstream methods.

show abstract

“…There are two early surveys of image deraining [4], [6] that mainly review prior-based and CNN-based methods. In comparison to recent survey [7] that reviews current methods from different perspectives, this paper seeks to provide much more than a summary of recent research progress. Although these surveys have provided comprehensive analyses of existing datasets, they still overlook two key factors when evaluting existing algorithms: synthetic dataset quality and common evaluation criteria.…”

Section: Relations With Other Surveysmentioning

confidence: 99%

“…A large number of deraining methods and benchmark datasets have been proposed in recent years with demonstrated success. Since this topic booms with the deep learning techniques [4], [5], [6], [7], it is significant to timely and comprehensively evaluate the state-of-the-art approaches to demonstrate their strength and weakness, thus facilitating the future development of this research field for more robust algorithms.…”

Section: Introductionmentioning

confidence: 99%

“…Returning to the problem itself, it is urgent and necessary to establish a high-quality benchmark and pave the way for future research in this field. Despite lots of efforts have been made on existing benchmarks [4], [5], [6], [7], [17], there still exist several potential challenges. According to statistics in Figure 1(b), existing methods usually use individual evaluation settings to evaluate the deraining performance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unpaired Deep Image Deraining Using Dual Contrastive Learning

Chen

Pan

Jiang

et al. 2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

131

View full text Add to dashboard Cite

Recent years have witnessed significant advances in image deraining due to the kinds of effective image priors and deep learning models. As each deraining approach has individual settings (e.g., training and test datasets, evaluation criteria), how to fairly evaluate existing approaches comprehensively is not a trivial task. Although existing surveys aim to review of image deraining approaches comprehensively, few of them focus on providing unify evaluation settings to examine the deraining capability and practicality evaluation. In this paper, we provide a comprehensive review of existing image deraining method and provide a unify evaluation setting to evaluate the performance of image deraining methods. We construct a new high-quality benchmark named HQ-RAIN to further conduct extensive evaluation, consisting of 5,000 paired high-resolution synthetic images with higher harmony and realism. We also discuss the existing challenges and highlight several future research opportunities worth exploring. To facilitate the reproduction and tracking of the latest deraining technologies for general users, we build an online platform to provide the off-the-shelf toolkit, involving the large-scale performance evaluation. This online platform and the proposed new benchmark are publicly available and will be regularly updated at http://www.deraining.tech/.

show abstract

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

Cited by 5 publications

References 138 publications

Black-box Dehazing Network via Joint Loss Function

Black-box Dehazing Network via Joint Loss Function

Recursive attention collaboration network for single image de‐raining

Unpaired Deep Image Deraining Using Dual Contrastive Learning

Contact Info

Product

Resources

About