Towards Spatially Disentangled Manipulation of Face Images With Pre-Trained StyleGANs | |
Yunfan Liu1,2; Qi Li2; Qiyao Deng2; Zhenan Sun1,2 | |
发表期刊 | IEEE Transactions on Circuits and Systems for Video Technology |
2023-04 | |
卷号 | 33期号:4页码:1725-1739 |
摘要 | Generative Adversarial Networks with style-based generators could successfully synthesize realistic images from input latent code. Moreover, recent studies have revealed that interpretable translations of generated images could be obtained by linearly traversing in the latent space. However, in most existing latent spaces, linear interpolation often leads to ‘spatially entangled modification’ in the manipulation result, which is undesirable in many real-world applications where local editing is required. To solve this problem, we propose to manipulate the latent code in the ‘style space’ and analyze its advantage in achieving spatial disentanglement. Furthermore, we point out the weakness of simply interpolating in the style space and propose ‘Style Intervention’, a lightweight optimization-based algorithm, to further improve the visual fidelity of manipulation results. The performance of our method is verified with the task of attribute editing on high-resolution face images. Both qualitative and quantitative results demonstrate the advantage of image translation in the style space and the effectiveness of our method on both real and synthetic images. |
收录类别 | SCI |
语种 | 英语 |
WOS记录号 | WOS:000970594600017 |
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/52072 |
专题 | 智能感知与计算研究中心 |
通讯作者 | Qi Li |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences 2.National Laboratory of Pattern Recognition, Center for Research on Intelligent Perception and Computing, Institute of Automation, Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yunfan Liu,Qi Li,Qiyao Deng,et al. Towards Spatially Disentangled Manipulation of Face Images With Pre-Trained StyleGANs[J]. IEEE Transactions on Circuits and Systems for Video Technology,2023,33(4):1725-1739. |
APA | Yunfan Liu,Qi Li,Qiyao Deng,&Zhenan Sun.(2023).Towards Spatially Disentangled Manipulation of Face Images With Pre-Trained StyleGANs.IEEE Transactions on Circuits and Systems for Video Technology,33(4),1725-1739. |
MLA | Yunfan Liu,et al."Towards Spatially Disentangled Manipulation of Face Images With Pre-Trained StyleGANs".IEEE Transactions on Circuits and Systems for Video Technology 33.4(2023):1725-1739. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Towards_Spatially_Di(10050KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论