计算机技术与发展2024，Vol.34Issue(4)：55-61,7.DOI:10.20165/j.cnki.ISSN1673-629X.2024.0009
基于多尺度Scale-Unet的单样本图像翻译
Single-sample Image Translation Based on Multi-scale Scale-Unet
摘要
Abstract
Single-sample unsupervised image-to-image translation(UI2I)has made significant progress with the development of generative adversarial networks(GANs).However,previous methods cannot capture complex textures in images and preserve original content information.We propose a novel one-shot image translation structure SUGAN based on a scale-variable U-Net structure(Scale—Unet).The proposed SUGAN uses Scale—Unet as a generator to continuously improve the network structure using multi-scale structures and progressive methods to learn image features from coarse to fine.Meanwhile,we propose the scale-pixel loss to better constrain the preservation of original content information and prevent information loss.Experiments show that compared with SinGAN,TuiGAN,TSIT,StyTR2 and another methods on public datasets Summer↔ Winter,Horse↔Zebra,the SIFID value of the generated image is reduced by 30％.The proposed method can better preserve the content information of the image while generating detailed and realistic high-quality images.关键词
单样本图像翻译/Scale-Unet/多尺度结构/渐进方法/尺度像素损失Key words
single-sample image translation/Scale-Unet/multi-scale structure/progressive approach/scale-pixel loss分类
信息技术与安全科学引用本文复制引用
周蓬勃,冯龙,寇宇帆..基于多尺度Scale-Unet的单样本图像翻译[J].计算机技术与发展,2024,34(4):55-61,7.基金项目
国家自然科学基金项目(62271393) （62271393）
国博文旅部重点实验室开放课题(CRRT2021K01) （CRRT2021K01）
陕西省重点研发计划(2019GY-215,2021ZDLSF06-04) （2019GY-215,2021ZDLSF06-04）
