BriefGPT.xyz
Aug, 2024
GRPose:通过姿势先验学习人像生成的图关系
GRPose: Learning Graph Relations for Human Image Generation with Pose Priors
HTML
PDF
Xiangchen Yin, Donglin Di, Lei Fan, Hao Li, Chen Wei...
TL;DR
本研究解决了现有基于扩散模型的人像生成方法在姿势一致性方面的不足。我们提出了一种利用姿势先验的图关系框架,通过构建姿势先验与扩散模型潜在表示之间的图拓扑结构,学习姿势部位间的内在关联。实验结果表明,该方法在姿势平均精度上相比最新基准模型提高了9.98%。
Abstract
Recent methods using
Diffusion Models
have made significant progress in
Human Image Generation
with various additional controls such as
Pose Prio
→