Image motion deblurring via attention generative adversarial network

Zhang, Yucun; Li, Tao; Li, Qun; Fu, Xiang; Kong, Tao

doi:10.1016/j.cag.2023.01.007

Cited by 5 publications

(3 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al [2] introduce a single-stage image motion deblurring method, effectively extracting local features but somewhat lacking in global context processing. Their approach, utilizing a residual module, a cascade cross-attention module, and a two-scale discriminator module, enhances detail processing.…”

Section: Related Workmentioning

confidence: 99%

“…Recent advancements in deep learning have spurred the development of numerous image deblurring methods, particularly those using convolutional neural networks (CNNs), which show remarkable proficiency in handling dynamic blur [1]. Zhang et al's [2] method for single-stage image motion deblurring excels in extracting local feature information, yet it somewhat lacks in addressing global contextual relationships. Lian et al's [3] U-Netbased [4] image deblurring method, enhanced with an attention mechanism, focuses more on local details.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CNB Net: A Two-Stage Approach for Effective Image Deblurring

Zhang,

Zheng,

Jiang

et al. 2024

Electronics

View full text Add to dashboard Cite

Image blur, often caused by camera shake and object movement, poses a significant challenge in computer vision. Image deblurring strives to restore clarity to these images. Traditional single-stage methods, while effective in detail enhancement, often neglect global context in favor of local information. Yet, both aspects are crucial, especially in real-life scenarios where images are typically large and subject to various blurs. Addressing this, we introduce CNB Net, an innovative deblurring network adept at integrating global and local insights for enhanced image restoration. The network operates in two stages, utilizing our specially designed Convolution and Normalization-Based Block (CNB Block) and Convolution and Normalization-Based Plus Block (CNBP Block) for multi-scale information extraction. A progressive learning approach is adopted with a Feature Active Selection (FAS) module at the end of each stage that captures spatial detail information under the guidance of real images. The Two-Stage Feature Fusion (TSFF) module reduces information loss caused by downsampling operations while enriching features across stages for increased robustness. We conduct experiments on the GoPro dataset and the HIDE dataset. On the GoPro dataset, our Peak Signal-to-Noise Ratio (PSNR) result is 32.21 and the Structural Similarity (SSIM) result is 0.950; and on the HIDE dataset, our PSNR result is 30.38 and the SSIM result is 0.932. Our results exceed other similar algorithms. By comparing the generated feature maps, we find that our model takes into account both global and local information well.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

CNB Net: A Two-Stage Approach for Effective Image Deblurring

Zhang,

Zheng,

Jiang

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Therefore, in this study, GAN-based image deblurring networks and UAV image domains are utilized to differentiate them from existing studies by solving problems through image post-processing rather than a hardware approach. Typically, to employ GAN for image deblurring, a dataset consisting of paired sharp and blurred images is required [26]. However, in the case of images captured by UAVs, reference images are often unavailable, necessitating the artificial synthesis of blurred images by combining consecutive frames [27].…”

Section: Introductionmentioning

confidence: 99%

A Motion Deblurring Network for Enhancing UAV Image Quality in Bridge Inspection

Lee,

Gwon,

Kim

et al. 2023

Drones

View full text Add to dashboard Cite

Unmanned aerial vehicles (UAVs) have been increasingly utilized for facility safety inspections due to their superior safety, cost effectiveness, and inspection accuracy compared to traditional manpower-based methods. High-resolution images captured by UAVs directly contribute to identifying and quantifying structural defects on facility exteriors, making image quality a critical factor in achieving accurate results. However, motion blur induced by external factors such as vibration, low light conditions, and wind during UAV operation significantly degrades image quality, leading to inaccurate defect detection and quantification. To address this issue, this research proposes a deblurring network using a Generative Adversarial Network (GAN) to eliminate the motion blur effect in UAV images. The GAN-based motion deblur network represents an image inpainting method that leverages generative models to correct blurry artifacts, thereby generating clear images. Unlike previous studies, this proposed approach incorporates deblur and blur learning modules to realistically generate blur images required for training the generative models. The UAV images processed using the motion deblur network are evaluated using a quality assessment method based on local blur map and other well-known image quality assessment (IQA) metrics. Moreover, in the experiment of crack detection utilizing the object detection system, improved detection results are observed when using enhanced images. Overall, this research contributes to improving the quality and accuracy of facility safety inspections conducted with UAV-based inspections by effectively addressing the challenges associated with motion blur effects in UAV-captured images.

show abstract

Aerial image deblurring via progressive residual recurrent network

Liu,

Zhang,

et al. 2024

SIViP

View full text Add to dashboard Cite

Image motion deblurring via attention generative adversarial network

Cited by 5 publications

References 42 publications

CNB Net: A Two-Stage Approach for Effective Image Deblurring

CNB Net: A Two-Stage Approach for Effective Image Deblurring

A Motion Deblurring Network for Enhancing UAV Image Quality in Bridge Inspection

Aerial image deblurring via progressive residual recurrent network

Contact Info

Product

Resources

About