4.7 Article Proceedings Paper

Transfiguring Portraits

期刊

ACM TRANSACTIONS ON GRAPHICS
卷 35, 期 4, 页码 -

出版社

ASSOC COMPUTING MACHINERY
DOI: 10.1145/2897824.2925871

关键词

face; big data; in the wild; appearance prediction; internet-based composites; portrait; imaginative

向作者/读者索取更多资源

People may look dramatically different by changing their hair color, hair style, when they grow older, in a different era style, or a different country or occupation. Some of those may transfigure appearance and inspire creative changes, some not, but how would we know without physically trying? We present a system that enables automatic synthesis of limitless numbers of appearances. A user inputs one or more photos (as many as they like) of his or her face, text queries an appearance of interest (just like they'd search an image search engine) and gets as output the input person in the queried appearance. Rather than fixing the number of queries or a dataset our system utilizes all the relevant and searchable images on the Internet, estimates a doppelganger set for the inputs, and utilizes it to generate composites. We present a large number of examples on photos taken with completely unconstrained imaging conditions.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据