Learning Blind Denoising Network for Noisy Image Deblurring

Chen, Meiya; Chang, Yi; Cao, Shuning; Yan, Luxin

doi:10.1109/icassp40776.2020.9053539

Cited by 10 publications

(11 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, [19] is not suitable for the space-variant situation. Wu [20] used two subnetworks for deblurring, where the first network estimates the linear kernel for each pixel and the second network is used for deblurring. Brehm [21] used a two-step strategy for video deblurring; single image deblurring is performed first, and then a temporal fusion is applied for better performance.…”

Section: B Learning-based Methodsmentioning

confidence: 99%

A Two-Stage Network for Image Deblurring

Tan

2021

IEEE Access

View full text Add to dashboard Cite

Blind deblurring is a typical challenge in image processing, carried out to correct various complex types of distortions that occur in the real world. Although learning-based deblurring methods have substantially outperformed the traditional algorithms, they fail to make full use of image priors, leading to inconsistent data distributions between the restored images and sharp images. In this paper, we divide the deblurring process into two steps and propose a two-stage network. The first stage generates an initial deblurred image using a common convolutional network. The second stage converts the initial data distribution into a latent sharp image distribution to obtain sharp edges through a prior network. Moreover, we propose a relativistic training strategy to train the prior network, which aims to learn the latent sharp image priors. In addition, we use a coarse-to-fine multiscale framework that shares weights between the different scales. The experimental results show that compared with other state-of-the-art methods, our method achieves competitive performances on benchmark datasets.

show abstract

Section: B Learning-based Methodsmentioning

confidence: 99%

A Two-Stage Network for Image Deblurring

Tan

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The weighted total variational priori based on graphs were proposed to promote bimodal gradient distribution of intermediate images. Recently, deep-learning-based methods have also achieved great progress in image deblurring [29][30][31][32][33][34][35].…”

Section: Related Workmentioning

confidence: 99%

Nonlinear Deblurring for Low-Light Saturated Image

Cao

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Single image deblurring has achieved significant progress for natural daytime images. Saturation is a common phenomenon in blurry images, due to the low light conditions and long exposure times. However, conventional linear deblurring methods usually deal with natural blurry images well but result in severe ringing artifacts when recovering low-light saturated blurry images. To solve this problem, we formulate the saturation deblurring problem as a nonlinear model, in which all the saturated and unsaturated pixels are modeled adaptively. Specifically, we additionally introduce a nonlinear function to the convolution operator to accommodate the procedure of the saturation in the presence of the blurring. The proposed method has two advantages over previous methods. On the one hand, the proposed method achieves the same high quality of restoring the natural image as seen in conventional deblurring methods, while also reducing the estimation errors in saturated areas and suppressing ringing artifacts. On the other hand, compared with the recent saturated-based deblurring methods, the proposed method captures the formation of unsaturated and saturated degradations straightforwardly rather than with cumbersome and error-prone detection steps. Note that, this nonlinear degradation model can be naturally formulated into a maximum-a posterioriframework, and can be efficiently decoupled into several solvable sub-problems via the alternating direction method of multipliers (ADMM). Experimental results on both synthetic and real-world images demonstrate that the proposed deblurring algorithm outperforms the state-of-the-art low-light saturation-based deblurring methods.

show abstract

“…Deep learning-based techniques have been widely utilised in image sample estimation [3,19,21,35,80], style transfer [20,107], super-resolution [6,30,46,55,96,102,108,124], and many other applications [78]. Image sample estimation is used to counter data limitation problems by developing synthetic data with similar data distribution.…”

Section: Introductionmentioning

confidence: 99%

Multi‐scale GAN with residual image learning for removing heterogeneous blur

Khan

Luo

2022

IET Image Processing

View full text Add to dashboard Cite

Processing images with heterogeneous blur remains challenging due to multiple degradation aspects that could affect structural properties. This study proposes a deep learning‐based multi‐scaled generative adversarial network (GAN) with residual image learning to process variant and in‐variant blur. Different scaled images with corresponding gradients are concatenated as a multi‐channel single input for the proposed GAN. Residual‐ and dense‐networks are combined to explore salient features in the bottleneck section while addressing the vanishing gradient problem. A hybrid content loss function with a gradient penalty minimises the error between generated and ground truth images. Due to structure sparsity, the generated output may lose some information that leads to artifacts. Residual image learning with dilation and end‐to‐end training is used to resolve this issue by recovering high‐resolution anatomical details. Three different datasets: GoPro, Köhler, and Lai, with variant and in‐variant blur, are used to perform qualitative and quantitative analyses. Experiments show the proposed method is effective in reducing blur while preserving structural properties compared to multiple preprocessing techniques for image analysis. Moreover, the consistently improved performance over multiple publicly available datasets validates the merits of the proposed method for large data analysis.

show abstract

Learning Blind Denoising Network for Noisy Image Deblurring

Cited by 10 publications

References 21 publications

A Two-Stage Network for Image Deblurring

A Two-Stage Network for Image Deblurring

Nonlinear Deblurring for Low-Light Saturated Image

Multi‐scale GAN with residual image learning for removing heterogeneous blur

Contact Info

Product

Resources

About