返回
A Generative Adversarial Network for Multistyle Unsupervised Image Transfer Based on Dynamic Position Normalization
DOI:10.1109/ACCESS.2022.3205013.png)
摘要
En 中文
Image transfer is a technology that changes the image effect by processing the image's color, contour, line, and other information. To stylize the visual appearance of the output will be adapted to the subject of the original image, this paper proposes an image feature transfer method called Cycle-DPN-GAN, based on the Cycle-Consistent Adversarial Networks. Firstly, Positional Normalization-Dynamic Moment Shortcut (PONO-DMS) module is introduced to learn more structural information from the input image, and the edge blurring and object losing are efficiently alleviated. In addition, the Multi-Scale-Structural Similarity Index (MS-SSIM) loss is added to the reconstruction loss, which improves visual perceptions and enhances the constraints on the reconstructed image in terms of image brightness, color contrast and structure. In this model, to verify the feasibility and superiority of the proposed method, the data sets of monet2photo, vangogh2photo, ukiyoe2photo and cezanne2photo are performed in the experiments, and the Inception Score and Frechet Inception Distance evaluation index are improved. In addition, ablation studies are performed to demonstrate the validity of each proposed component. In this paper, the results of the quantitative evaluation are consistent with the qualitative evaluation. It can be demonstrated that the images generated by Cycle-DPN-GAN have higher visual quality.
Keyword:
Generators
Deep learning
Image reconstruction
Generative adversarial networks
Decoding
Painting
Visualization
CycleGAN
deep learning
generative adversarial network
image transfer
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
The Effect of 40-Hz Light Therapy on Amyloid Load in Patients with Prodromal and Clinical Alzheimer’s Disease40Hz光疗法对前驱和临床阿尔茨海默病患者淀粉样蛋白负荷的影响

