摘要
针对普通生成模型生成的图片存在细节缺乏、图片模糊等问题,结合变分自编码器(VAE)强大的特征提取能力,使用条件生成对抗网络(CGAN)生成了高质量照片,结果表明,利用该方法基于CUHK student人脸库生成照片,照片的相似性度提高了0.09,达到了0.77。同时在实际应用中,手绘素描由于画家的不同而风格迥异,在训练素描-照片生成过程中使用同一风格的素描会使得输入图像单一。为避免这一问题,通过使用多种素描样式扩展训练数据集,提高了模型通用性,结果表明,相比于未扩展训练集,基于扩展训练集生成的照片的相似性度提高了0.233,达到了0.603。
The traditional generation model causes image blurring and lack of details.Therefore,in this paper,we propose a conditional generation adversarial network combining with the powerful feature extraction capability of the variational autoencoder to realize high-quality photo generation.In training process of sketch-photo generation,sketches with the same style are used,leading to the monotonous input image.The hand-drawn sketches of various artists have different styles.Therefore,using sketches in multiple styles to extend the training dataset,the universality of the model is improved.The experimental results demonstrate that the similarity of the generated photos using the proposed method improves by 0.09(to 0.77)based on CUHK student data set.In addition,the compared with the unexpanding training set,the similarity of the generating image using our training set also improves by 0.233(to 0.603).
作者
崔小曼
于凤芹
Cui Xiaoman;Yu Fengqin(School of Internet of Things Engineering,Jiangnan University,Wuaci,Jiangsu 214122,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2020年第18期189-195,共7页
Laser & Optoelectronics Progress
基金
国家自然科学基金(61573168)
中央高校基本科研业务费专项资金(JUSRP51733B)。
关键词
图像处理
变分自编码器
条件生成对抗网络
素描
image processing
variational auto-encoder
conditional gencration adversarial networks
sketch
