A Criminisi-DnCNN Model-Based Image Inpainting Method

Li, Zun; Zhu, Yuanpei; Wang, Yuping

doi:10.1155/2022/9780668

Cited by 3 publications

(4 citation statements)

References 25 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DnCNN is widely used in the field of image denoising. Li et al [38] addressed the problem of image inpainting by transforming it into an image denoising…”

Section: Denoising Convolutional Neural Network (Dncnn)mentioning

confidence: 99%

“…DnCNN is widely used in the field of image denoising. Li et al [38] addressed the problem of image inpainting by transforming it into an image denoising problem and utilized DnCNN to restore the missing parts of the image edges. Wei et al [39] proposed a fast block based evolutionary denoising convolutional neural network (FBE-DnCNN) to enhance the competitiveness of image denoising.…”

Section: Denoising Convolutional Neural Network (Dncnn)mentioning

confidence: 99%

See 1 more Smart Citation

Noise Attenuation for CSEM Data via Deep Residual Denoising Convolutional Neural Network and Shift-Invariant Sparse Coding

Wang,

Bai,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

To overcome the interference of noise on the exploration effectiveness of the controlled-source electromagnetic method (CSEM), we improved the deep learning algorithm by combining the denoising convolutional neural network (DnCNN) with the residual network (ResNet), and propose a method based on the residual denoising convolutional neural network (ResDnCNN) and shift-invariant sparse coding (SISC) for denoising CSEM data. Firstly, a sample library was constructed by adding simulated noises of different types and amplitudes to high-quality CSEM data collected. Then, the sample library was used for model training in the ResDnCNN, resulting in a network model specifically designed for denoising CSEM data. Subsequently, the trained model was employed to denoise the measured data, generating preliminary denoised data. Finally, the preliminary denoised data was processed using SISC to obtain the final denoised high-quality data. Comparative experiments with the ResNet, DnCNN, U-Net, and long short-term memory (LSTM) networks demonstrated the significant advantages of our proposed method. It effectively removed strong noise such as Gaussian, impulse, and square wave, resulting in an improvement of the signal-to-noise ratio by nearly 20 dB. Testing on CSEM data from Sichuan Province, China, showed that the apparent resistivity curves plotted using our method were smoother and more credible.

show abstract

“…DnCNN is widely used in the field of image denoising. Li et al [38] addressed the problem of image inpainting by transforming it into an image denoising…”

Section: Denoising Convolutional Neural Network (Dncnn)mentioning

confidence: 99%

Section: Denoising Convolutional Neural Network (Dncnn)mentioning

confidence: 99%

Noise Attenuation for CSEM Data via Deep Residual Denoising Convolutional Neural Network and Shift-Invariant Sparse Coding

Wang,

Bai,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Criminisi et al propose a texture synthesis method [11] ,which is mainly implemented by repeatedly computing the priority of the restored region [12] , propagating the texture information and updating the confidence level, but with the consequent repetition of steps, the confidence level decreases, leading to errors in the filling order.…”

Section: Patch-based Approachmentioning

confidence: 99%

Autonomous unsupervised image inpainting networks based on structural priors

Huang

Wang

2023

3rd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2023)

View full text Add to dashboard Cite

Deep convolutional networks have become a popular tool for image generation and restoration.In general, their outstanding performance is attributed to their ability to learn real image priors from a large number of example images.Many seemingly unrelated computer vision tasks can be viewed as special cases of image decomposition into independent layers.Image segmentation (divided into foreground layer and background layer); transparent layer separation (divided into reflection layer and transmission layer); image dehazing (separation into clear image and haze map), etc.Nowadays, in the field of image restoration using deep learning, there are many low-quality images, but the corresponding original pictures are fewer, which makes image restoration based on deep learning one of the more difficult problems in the field of computer vision.In order to break through the related problems, this paper abandons the supervised deep learning method based on a large amount of data training and then proposes an autonomous unsupervised image inpainting network, Fast-RDDIP, based on structure prior.This ability stems from the fact that the internal statistics of a mixture of layers are more complex than the statistics of each individual component.Consequently, this study constructs a matching network structure using the characteristics of various learning distribution rates of the network and additional convolution, which has characteristics like shared parameters. can perform end-to-end training.This essay explains how this technique improves image quality and dehazing. According to the experimental findings on the O-Haze dataset, Fast-RDDIP performs better than more established methods like SIHR, EIDBC, supervised neural networks like DehazeNet, NTDF, NLD, URIE, and BOPBL, as well as unsupervised neural networks like DoubleDIP models.

show abstract

“…Recent advances in artificial intelligence have led to the development of new methods for picture restoration. Zun Li et al 12 proposed a repair method based on the Criminisi DnCNN model to address the issue of suboptimal image repair in specific areas. Zhao Yang Jia et al 13 used multispectral image decomposition and synthesis to establish a technique for digital image repair that provides a robust foundation for defect repair, digital archiving, and high-fidelity reproduction of works of art.…”

Section: Introductionmentioning

confidence: 99%

Image restoration technology of Tang Dynasty tomb murals based on adversarial edge learning

Yan

Zhang

He³

et al. 2023

Preprint

View full text Add to dashboard Cite

Xi'an, China houses a vast collection of valuable Tang dynasty (618AD-907AD) tomb murals that have experienced various degrees of damage over time due to weathering. This research proposes an adversarial edge learning-based mural restoration technique that provides a fast and accurate automatic repair of the murals. The method uses generative adversarial networks to learn how to repair the edge contour of the damaged mural and restore the missing content. The contour restoration network and the mural restoration network are trained and updated simultaneously to enhance the feature extraction and restoration coordination performance of the network. The experiments were conducted on a self-built Tang dynasty tomb mural painting restoration dataset and compared to several existing algorithms. The proposed algorithm showed a 1.3 increase in Peak Signal to Noise Ratio (PSNR) and a 1.43% increase in Structural Similarity (SSIM) value, providing a precise restoration of the structure and contour of the mural content. The algorithm successfully repaired damaged murals with fractures and small parts breaking off. The suggested method can be useful for both the technical repair and conservation of significant national visual cultural property and the digital restoration of historic murals.

show abstract

A Criminisi-DnCNN Model-Based Image Inpainting Method

Cited by 3 publications

References 25 publications

Noise Attenuation for CSEM Data via Deep Residual Denoising Convolutional Neural Network and Shift-Invariant Sparse Coding

Noise Attenuation for CSEM Data via Deep Residual Denoising Convolutional Neural Network and Shift-Invariant Sparse Coding

Autonomous unsupervised image inpainting networks based on structural priors

Image restoration technology of Tang Dynasty tomb murals based on adversarial edge learning

Contact Info

Product

Resources

About