Research on image inpainting algorithm of improved total variation minimization method

Chen, Yuantao; Zhang, Haopeng; Liu, Linwu; Tao, Jiajun; Zhang, Qian; Yang, Kai; Xia, Runlong; Xie, Jiang

doi:10.1007/s12652-020-02778-2

Cited by 58 publications

(31 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Super resolution has a good future in various fields, such as military industry, agriculture, or medicine. Super resolution plays an important role in the field of artificial intelligence [1][2]. This paper focuses on the introduction of Single Image Super-Resolution (SISR) technology, which has been widely used in image compression, medical imaging [3][4][5], remote sensing imaging [6], public security [7] and other fields due to its flexibility, simplicity and high practicability.…”

Section: Introductionmentioning

confidence: 99%

A Super Resolution Algorithm Based on Attention Mechanism and SRGAN Network

Liu¹,

Chen²

2021

IEEE Access

View full text Add to dashboard Cite

Image super-resolution reconstruction uses a specific algorithm to restore the low resolution blurred image in the same scene to a high resolution image. In recent years, with the vigorous development of deep learning, this technology has been widely used in many fields. In the field of image super-resolution reconstruction, more and more methods based on deep learning have been studied. According to the principle of GAN, a pseudo high-resolution image is generated by the generator, and then the discriminator calculates the difference between the image and the real high-resolution image to measure the authenticity of the image. Based on SRGAN (super resolution general adverse network), this paper mainly makes three improvements. First, it introduces the attention channel mechanism, that is, it adds Ca (channel attention) module to SRGAN network, and increases the network depth to better express high frequency features; Second, delete the original BN (batch normalization) layer to improve the network performance; Third, modify the loss function to reduce the impact of noise on the image. The experimental results show that the proposed method is superior to the current methods in both quantitative and qualitative indicators, and promotes the recovery of high-frequency detail information. The experimental results show that the proposed method improves the artifact problem and improves the PSNR (peak signal-to-noise ratio) on set5, set10 and bsd100 test sets.

show abstract

Section: Introductionmentioning

confidence: 99%

A Super Resolution Algorithm Based on Attention Mechanism and SRGAN Network

Liu¹,

Chen²

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Kim et al [3], [4] then improved the network depth of Super-Resolution using Very Deep Convolutional Networks (VDSR) and a deeply recursive convolution network (DRCN) for image super-resolution to 20 levels, and eased the training difficulty by introducing residual learning. Chen et al [5]- [10] introduced an attention mechanism in the network and improved the original convolutional neural network. Because convolutional neural network (CNN)based methods [16], [18], [28]- [34] achieve an excellent performance based on indicators such as the peak signal-tonoise ratio (PSNR) and structural similarity (SSIM), which can reflect the pros and cons of a super-resolution reconstruction, many different types of CNN-based methods have been proposed.…”

Section: Introductionmentioning

confidence: 99%

RBDN: Residual Bottleneck Dense Network for Image Super-Resolution

Zhang

Sheng

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Recent studies have shown that a super-resolution generative adversarial network (SRGAN) can significantly improve the quality of single-image super-resolution. However, existing SRGAN methods also have certain drawbacks, such as an insufficient feature utilization, a large number of parameters. To further enhance the visual quality, we thoroughly studied three key components of SRGAN, i.e., the network architecture, adversarial loss, and perceptual loss, and propose a DenseNet with Residual-in-Residual Bottleneck Block (RRBB), called a residual bottleneck dense network (RBDN), for single-image superresolution. First, to improve the utilization of features between the various layers of the network, we adopted a dense cascading connection between layers. At the same time, to reduce the computational cost, we added a bottleneck structure to each layer, greatly reducing the number of network parameters and accelerating the convergence speed of the training process. Second, the proposed RRBB, as the basic network building unit, removes the batch normalization (BN) layer and employs the ELU function to reduce the opposite effects in the absence of BN. In addition, we applied an improved overall loss function during the model training process to stably train the model and further improve the realism of the reconstructed high-resolution image. To prove the superiority of our proposed model, we conducted a comprehensive and objective evaluation of the Peak Signal-to-Noise Ratio, structural similarity, learned perceptual image patch similarity, and other evaluation indicators obtained from the three test sets, i.e., Set5, Set14, and BSD100, from the recent stateof-the-art model. Finally, we conducted qualitative and quantitative analyses of the results obtained in terms of the evaluation indicators, the authenticity of the restored HR images, and textural details, which show the superiority of the RBDN model.

show abstract

“…The total variation prior (TV) [34]- [38] is widely used in image deblurring, image denoising, and image MFSR. However, this prior will produce stair effects in the smooth area of images under strong noise.…”

Section: Introductionmentioning

confidence: 99%

Dark Channel Based Multiframe Super-Resolution Reconstruction

et al. 2021

View full text Add to dashboard Cite

Multiframe super-resolution (MFSR) can obtain a high-resolution image from a set of lowresolution images. The performance of super-resolution is affected by the image prior information. The current super-resolution algorithms typically use total variation prior and its improved version, restoring the image edges well. However, it will produce artifacts and stair effects in the smooth region of the image. Therefore, we propose a dark channel-based MFSR algorithm to achieve edge-preserving and noisesuppressing. Firstly, the total variation prior is used to ensure the edge-preserving ability of the algorithm. Secondly, the dark channel prior is added to suppress artifacts and stair effects. Finally, the weights of the prior terms are iteratively adapted to obtain the final high-resolution image. Experiments show that the proposed algorithm can achieve a better result in objective and subjective visual evaluations.INDEX TERMS Image process, multiframe super-resolution, dark channel prior, total variation prior, image prior combination, Bayesian framework.

show abstract

Research on image inpainting algorithm of improved total variation minimization method

Cited by 58 publications

References 42 publications

A Super Resolution Algorithm Based on Attention Mechanism and SRGAN Network

A Super Resolution Algorithm Based on Attention Mechanism and SRGAN Network

RBDN: Residual Bottleneck Dense Network for Image Super-Resolution

Dark Channel Based Multiframe Super-Resolution Reconstruction

Contact Info

Product

Resources

About