A GAN-based Denoising Method for Chinese Stele and Rubbing Calligraphic Image

Wang, Xuanhong; Wu, Kun; Zhang, Ying; Xiao, Yun; Xu, Pengfei

doi:10.1007/s00371-022-02410-8

Cited by 5 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, we can make full use of the Wasserstein distance to make the estimated residual histograms as close as possible to the reference Gaussian noise histogram, so as to improve the residual estimation accuracy. As we know, the training of the GAN based denoising network [45]- [47] is to minimize the weighted sum of the content loss and adversarial loss. However, the proposed MRWM is a model based image denoising method which ably combines the multiple residual Wasserstein constraints and image prior regularization.…”

Section: Motivationmentioning

confidence: 99%

MRWM: A Multiple Residual Wasserstein Driven Model for Image Denoising

Lan

Liu

2022

IEEE Access

View full text Add to dashboard Cite

Residual histograms can provide valuable information for vision research. However, current image restoration methods have not fully exploited the potential of multiple residual histograms, especially their role as overall regularization constraints. In this paper, we propose a novel framework of multiple residual Wasserstein driven model (MRWM) that can organically combine multiple residual Wasserstein constraints and various natural image priors for image denoising. Specifically, by utilizing the Wasserstein distance derived from the optimal transmission theory, the multiple residual histograms of the observed images are forced to be as close as possible to the reference residual histogram, thereby improving the accuracy of residual estimation. Furthermore, the proposed concrete MRWM unifies the multiple residual Wasserstein distribution approximation and the image total variation prior knowledge to carry out image denoising. Alternating iterative algorithm of histogram matching and Chambolle dual projection has the characteristics of less parameters and easy implementation. Finally, our experiments confirm that compared with some representative image denoising algorithms, the MRWM can obtain better performance in objective evaluation, and can better preserve the details such as the image edges, making the image look more natural.

show abstract

Section: Motivationmentioning

confidence: 99%

MRWM: A Multiple Residual Wasserstein Driven Model for Image Denoising

Lan

Liu

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Recently, Convolutional Neural Networks (CNN) [1][2][3] and Generative Adversarial Network (GAN) -based methods [4][5][6] have achieved impressive performance for the IR task. Although these IR techniques can generate appropriate content for missing regions according to the remaining image patches, these methods still face significant challenges such as blurry artifacts in image restoration causing unpleasant visual effects.…”

Section: Introductionmentioning

confidence: 99%

SIDM-WIR: A Sampling Improved DiffusionModel for Worksite Image Restoration

Wen,

Zhuang,

Deng

2024

Preprint

View full text Add to dashboard Cite

At presently, Diffusion Model (DM) has achieved state-of-the-art performanceby modeling the image synthesis process through a series of denoising networkapplications. Image Restoration (IR) is to improve the subjective image qual-ity corrupted by various kinds of degradation unlike image synthesis. However,IR for worksite images is greatly challenging in the low-level vision field due tocomplicated environmental factors. To solve this problem, we propose a Sam-pling Improved Diffusion Model for Worksite Image Restoration (SIDM-WIR).It not only improves the authenticity and representation ability for the gener-ation process, but also handles complex backgrounds and diverse object typeseffectively. SIDM-WIR has three main contributions: 1) Its framework adopts aMish-based residual module, which enhances the ability to learn complex patternsof images, and allows for the presence of negative gradients to reduce overfittingrisks during model training. 2) It employs a Mixed-head Self-Attention (MSA)mechanism, which augments the correlation among input elements at each timestep, and maintains a better balance between capturing the global structuralinformation and local detailed textures of the image. 3) It ran in a new customizeddataset named Workplace for WIR specifically. Furthermore, experiments on bothtwo datasets demonstrate that SIDM-WIR achieves better results to previousmethods both quantitatively and qualitatively.

show abstract

Cross-UNet: dual-branch infrared and visible image fusion framework based on cross-convolution and attention mechanism

Wang

Hua

2022

Vis Comput

View full text Add to dashboard Cite

A GAN-based Denoising Method for Chinese Stele and Rubbing Calligraphic Image

Cited by 5 publications

References 37 publications

MRWM: A Multiple Residual Wasserstein Driven Model for Image Denoising

MRWM: A Multiple Residual Wasserstein Driven Model for Image Denoising

SIDM-WIR: A Sampling Improved DiffusionModel for Worksite Image Restoration

Cross-UNet: dual-branch infrared and visible image fusion framework based on cross-convolution and attention mechanism

Contact Info

Product

Resources

About