Deep Convolutional-Neural-Network-Based Channel Attention for Single Image Dynamic Scene Blind Deblurring

Shengdao, Wan; Shu, Tang; Xie, Xianzhong; Gu, Jia; Huang, Rong; Ma, Bin; Luo, Lei

doi:10.1109/tcsvt.2020.3035664

Cited by 22 publications

(7 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the moment, the direction of using multiscale training looks promising, and other exciting results have already been obtained in [67][68][69]. We can separately note an attempt to use the attention mechanism to study the relationship between spatial objects and the channels on an image [70].…”

Section: Application Of Deep Learning In a Deconvolution Problemmentioning

confidence: 97%

State-of-the-Art Approaches for Image Deconvolution Problems, including Modern Deep Learning Architectures

Makarkin

Bratashov

2021

Micromachines

View full text Add to dashboard Cite

In modern digital microscopy, deconvolution methods are widely used to eliminate a number of image defects and increase resolution. In this review, we have divided these methods into classical, deep learning-based, and optimization-based methods. The review describes the major architectures of neural networks, such as convolutional and generative adversarial networks, autoencoders, various forms of recurrent networks, and the attention mechanism used for the deconvolution problem. Special attention is paid to deep learning as the most powerful and flexible modern approach. The review describes the major architectures of neural networks used for the deconvolution problem. We describe the difficulties in their application, such as the discrepancy between the standard loss functions and the visual content and the heterogeneity of the images. Next, we examine how to deal with this by introducing new loss functions, multiscale learning, and prior knowledge of visual content. In conclusion, a review of promising directions and further development of deconvolution methods in microscopy is given.

show abstract

Section: Application Of Deep Learning In a Deconvolution Problemmentioning

confidence: 97%

State-of-the-Art Approaches for Image Deconvolution Problems, including Modern Deep Learning Architectures

Makarkin

Bratashov

2021

Micromachines

View full text Add to dashboard Cite

show abstract

“…The radius of each circle denotes the model's number of parameters. Our method achieves high performance with real-time runtime and small parameters compared with state-of-the-art blind deblurring methods including MS-CNN [1], SRN [2], DMPHN [3], DeblurGAN [4], DeblurGANv2 [5], Gaoet al [6], MT-RNN [7], SAPHN [8], RADN [9], MSCAN [10] and MPRNet [11].…”

Section: High Performancementioning

confidence: 98%

“…SAPHN [8] combines the multi-patch hierarchical structure with global attention and adaptive local filters to learn the transformation of features in the deblurring process. MSCAN [10] proposes a channel-attention convolutional neural network for single image denblurring. Wang et al [35] propose a recursive video deblurring network, and MACNN [36] introduces the multi-attention mechanism to video deblurring.…”

Section: Related Workmentioning

confidence: 99%

Deep Idempotent Network for Efficient Single Image Blind Deblurring

Mao

Wan

Dai

et al. 2023

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Single image blind deblurring is highly ill-posed as neither the latent sharp image nor the blur kernel is known. Even though considerable progress has been made, several major difficulties remain for blind deblurring, including the trade-off between high-performance deblurring and real-time processing. Besides, we observe that current single image blind deblurring networks cannot further improve or stabilize the performance but significantly degrades the performance when re-deblurring is repeatedly applied. This implies the limitation of these networks in modeling an ideal deblurring process. In this work, we make two contributions to tackle the above difficulties:(1) We introduce the idempotent constraint into the deblurring framework and present a deep idempotent network to achieve improved blind non-uniform deblurring performance with stable re-deblurring. (2) We propose a simple yet efficient deblurring network with lightweight encoder-decoder units and a recurrent structure that can deblur images in a progressive residual fashion. Extensive experiments on synthetic and realistic datasets prove the superiority of our proposed framework. Remarkably, our proposed network is nearly 6.5× smaller and 6.4× faster than the state-of-the-art while achieving comparable high performance.

show abstract

“…Esmaeilzehi et al [34] proposed a two-stage convolutional network to carry out the processes of up-sampling and deblurring. For the dynamic scene blind deblurring problem, Wan et al [35] proposed a novel multi-scale channel attention network by using the spatial pyramid pooling channel attention strategy. Chakrabarti [36] presented a new blind motion deblurring network by predicting the Fourier coefficients of the deconvolution filter.…”

Section: Related Workmentioning

confidence: 99%

Blind Text Image Deblurring Algorithm Based on Multi-Scale Fusion and Sparse Priors

Yang

Cheng

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The goal of blind text image deblurring is to obtain a clean text image from the given blurry text image without knowing the blur kernel. Sparsity-based methods have been shown their effectiveness in various blind text image deblurring models. However, the blur kernel estimation methods based on sparse priors lack of the consideration for the brightness information about the blur kernel, which will affect the restoration effect of the blur kernel. Besides, previous methods seldom apply sparse priors to both spatial domain and transform domain information. We propose a novel blind text image deblurring model based on multi-scale fusion and sparse priors. Besides the sparse gradient prior on the latent clean text image, we add the sparse prior on the high-frequency wavelet coefficients of the latent text image, which will better constrain the solution space and obtain good clean images. The semi-quadratic splitting method is used to alternately optimize the blur kernel and the latent clean image. Meanwhile, we consider the influence of the brightness feature of the restored blur kernel. By multi-scale fusion technique on the basis of Laplacian weight and saliency weight, we fuse the computed blur kernels in three channels to improve the quality of blur kernel. The experimental results show that our algorithm has good results in the restoration of blur kernels and text images.INDEX TERMS Blind text image deblurring, sparse priors, multi-scale fusion, wavelet transform.

show abstract

Deep Convolutional-Neural-Network-Based Channel Attention for Single Image Dynamic Scene Blind Deblurring

Cited by 22 publications

References 41 publications

State-of-the-Art Approaches for Image Deconvolution Problems, including Modern Deep Learning Architectures

State-of-the-Art Approaches for Image Deconvolution Problems, including Modern Deep Learning Architectures

Deep Idempotent Network for Efficient Single Image Blind Deblurring

Blind Text Image Deblurring Algorithm Based on Multi-Scale Fusion and Sparse Priors

Contact Info

Product

Resources

About