DOI码：10.1111/cgf.14165

所属单位：BNRist, Department of Computer Science and Technology, Tsinghua University China

发表刊物：Computer Graphics Forum

项目来源：NSFC (61521002); Beijing Higher Institution ERC; Tsinghua-Tencent Joint Lab

摘要：Abstract Image‐to‐image translation has been widely studied. Since real‐world images can often be described by multiple attributes, it is useful to manipulate them at the same time. However, most methods focus on transforming between two domains, and when they chain multiple single attribute transform networks together, the results are affected by the order of chaining, and the performance drops with the out‐of‐domain issue for intermediate results. Existing multi‐domain transfer methods mostly manipulate multiple attributes by adding a list of attribute labels to the network feature, but they also suffer from interference of different attributes, and perform worse when multiple attributes are manipulated. We propose a novel approach to multi‐attribute image‐to‐image translation using several parallel latent transform networks, where multiple attributes are manipulated in parallel and simultaneously, which eliminates both issues. To avoid the interference of different attributes, we introduce a novel soft independence constraint for the changes caused by different attributes. Extensive experiments show that our method outperforms state‐of‐the‐art methods.

备注：Funding: National Natural Science Foundation of China (61521002); Research Grant of Beijing Higher Institution Engineering Research Center; Tsinghua-Tencent Joint Laboratory for Internet Innovation Technology; Other ISSNs: 1467-8659

合写作者：Yu-Kun Lai

第一作者：Sen-Zhe Xu

论文类型：期刊论文

学科门类：工学

文献类型：J

卷号：39

期号：7

页面范围：531–542

ISSN号：0167-7055

是否译文：否

发布期刊链接：https://onlinelibrary.wiley.com/doi/10.1111/cgf.14165