Total Selfie: Generating Full-Body Selfies
arxiv(2023)
摘要
We present a method to generate full-body selfies from photographs originally
taken at arms length. Because self-captured photos are typically taken close
up, they have limited field of view and exaggerated perspective that distorts
facial shapes. We instead seek to generate the photo some one else would take
of you from a few feet away. Our approach takes as input four selfies of your
face and body, a background image, and generates a full-body selfie in a
desired target pose. We introduce a novel diffusion-based approach to combine
all of this information into high-quality, well-composed photos of you with the
desired pose and background.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要