Image Deblurring based on Lightweight Multi-Information Fusion Network

Zhang, Yanni; Liu, Yiming; Li, Qiang; Qi, Miao; Xu, Dan; Kong, Jun; Jian-zhong, Wang

doi:10.1109/icip42928.2021.9506606

Cited by 4 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to recent rapid advancements in this field, deep learning has substantially surpassed conventional deraining techniques in single-image rain removal and other image restoration tasks. Data-driven based rain removal approaches include CNN based [24]- [35], Attention based [39]- [42] GANs OR Lightweight pyramid based [43]- [60]. [24] introduces a stereo-based rainy dataset and the Paired Rain Removal Network (PRRNet) for monocular deraining, addressing semantic segmentation and scene deraining challenges.…”

Section: B Data-driven Image Deraining Methodsmentioning

confidence: 99%

“…Lightweight pyramid networks are vital for efficient lowlevel image processing and computer vision tasks. Despite deep-CNNs' success in deraining, their parameter complexity is addressed by lightweight pyramids, utilized in various tasks like image deblurring [43] and lightweight super-resolution [44]. In [45] a lightweight pyramid network LPNet is introduced for SID using Gaussian-Laplacian decomposition and recursive-residual networks.…”

Section: B Data-driven Image Deraining Methodsmentioning

confidence: 99%

See 1 more Smart Citation

LPN-IDD: A Lightweight Pyramid Network for Image Deraining and Detection

Babar,

Yaseen,

Al-Shamayleh

et al. 2024

IEEE Access

View full text Add to dashboard Cite

One of the challenges in image processing involves single-image deraining (SID). Existing methods do not exploit images at multi-scales and often overlook spatial and channel information. These methods fail to account for different rain conditions, leading to challenges in effectively removing a wide range of rain streak patterns, such as diverse directional or dense streaks. Moreover, they often result in the loss of fine texture details or a blurred background in the process of eliminating rain streaks from images captured in heavy rain. Mostly state-of-the-art (SOTA) deraining models achieve higher performance in removing rain from rainy images but at the expense of a high number of parameters, which results in computational complexity and memory requirements. Furthermore, they also do not consider high-level visioned evaluation metrics to perform deep evaluations of the proposed models. In this paper, a simple lightweight network with few parameters and relatively shallow depth is proposed by fusing the traditional Gaussian-Laplacian pyramid technique with the attention module. We propose a novel attention-based lightweight pyramid network for image deraining and detection (LPN-IDD) to achieve better deraining performance. The proposed model includes a dual attention module integrated with the Gaussian-Laplacian pyramids network. In LPN-IDD, different levels of laplacian pyramids can extract multi-scale features to adapt to different shapes and types of rain streaks. Residual and recursive blocks are used in each subnetwork along with dual attention blocks to resist the occlusion or texture feature while suppressing unnecessary features. Extensive experimentation performed on the SID synthetic and real-world datasets demonstrate the effectiveness of the proposed model in image deraining tasks. For deep evaluation of the proposed methodology, object detection models including faster-RCNN, YOLO-V3, YOLO-V7 are used along with full reference evaluation metrics.

show abstract

Section: B Data-driven Image Deraining Methodsmentioning

confidence: 99%

Section: B Data-driven Image Deraining Methodsmentioning

confidence: 99%

LPN-IDD: A Lightweight Pyramid Network for Image Deraining and Detection

Babar,

Yaseen,

Al-Shamayleh

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Recently, the issue of lightweight models [74], [75] has caught the attention of researchers. For example, deep learning-based lightweight models have achieved excellent results in image denoising [76], deraining [77], deblurring [78], and dehazing [79] studies. Thus constructing lightweight demoiréing models is a potential research direction.…”

Section: A Model Light-weightingmentioning

confidence: 99%

Deep Learning for Screen-Shot Image Demoiréing: A Survey

Hou

Wang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Image demoiréing is an important image processing technology in computer vision, used to remove the moiré from images and improve the image quality. In recent years, the image demoiréing technique based on the deep learning method has gained more attention and achieved good results, but it still has some limitations. This paper aims to provide a review and perspective on the recent advances in deep learning-based image demoiréing techniques. First, the definition and production principle of the image moiré pattern are given. Common datasets and image quality evalution methods in demoiréing studies are analyzed. Then two internationally famous competitions in image demoiréing are introduced. Second, the research status of the supervised demoiréing technique is summarized from four dimensions: sampling method, model network design, baseline model, and training learning strategy. Recent progress made by the mainstream model of unsupervised deep learning in the field of image demoiréing is summarized. The typical application of the image demoiréing technique in panel defect detection and digital radiography is analyzed. The performance and the image quality of the above mentioned models based on different data sets are evaluated in detail. Finally, this paper analyzes and forelocks the problems to be solved in the coming years. INDEX TERMS Image demoiréing, screen-shot image, deep learning, convolutional neural networks (CNN)

show abstract

“…In addition, these traditional methods always consume tremendous computing resources and time. Later, data-driven strategies based on deep learning [5,6,7,8,9] are proposed. Due to the powerful fitting ability of deep learning, these methods can eliminate the constraints of traditional methods and learn a functional relationship that directly maps blur images to sharp images.…”

Section: Introductionmentioning

confidence: 99%

Efficient Deblurring Via High-Frequency and Low-Frequency Information Fusion

Yuan

Wang

2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

The distortion of high-frequency information is the most fundamental problem of dynamic scene blur, which leads to the degradation of image quality. However, most deep-based methods fail to show satisfactory results because of ignoring the importance of image structural information (highfrequency and low-frequency preception) in deblurring. In this paper, we propose a high-frequency and low-frequency information fusion deblurring network (HLFNet) that uses edge perception as a guide. The proposed HLFNet consists of the high-frequency information network (HFNet) and the low-frequency information network (LFNet). Besides, we adopt the proposed multi-scale atrous convolution (MSA) block into LFNet, which can effectively reduce the number of model parameters while expanding the receptive fields. Extensive experiments show that the proposed model can achieve state-of-the-art results with smaller parameters and shorter inference time on the public datasets.

show abstract

Image Deblurring based on Lightweight Multi-Information Fusion Network

Cited by 4 publications

References 24 publications

LPN-IDD: A Lightweight Pyramid Network for Image Deraining and Detection

LPN-IDD: A Lightweight Pyramid Network for Image Deraining and Detection

Deep Learning for Screen-Shot Image Demoiréing: A Survey

Efficient Deblurring Via High-Frequency and Low-Frequency Information Fusion

Contact Info

Product

Resources

About