BriefGPT.xyz
Apr, 2019
逐步姿态注意力转移用于人像生成
Progressive Pose Attention Transfer for Person Image Generation
HTML
PDF
Zhen Zhu, Tengteng Huang, Baoguang Shi, Miao Yu, Bofei Wang...
TL;DR
提出了一种新的生成式对抗网络,用于姿势转移,其生成器由一系列姿势注意传输块组成,可以生成具有更好外观一致性和形状一致性的图像,此方法能够为人物重新识别生成训练图像,并提高具体实现的效率和有效性。
Abstract
This paper proposes a new
generative adversarial network
for
pose transfer
, i.e., transferring the pose of a given person to a target pose. The generator of the network comprises a sequence of
→