BriefGPT.xyz
Apr, 2021
网格 Graphormer
Mesh Graphormer
HTML
PDF
Kevin Lin, Lijuan Wang, Zicheng Liu
TL;DR
本文提出一种名为Mesh Graphormer的图卷积强化Transformer,可从单张图像中重建3D人体姿势和网格。实验结果表明,该方法在多个基准测试中显著优于先前的最先进方法。
Abstract
We present a
graph-convolution-reinforced transformer
, named Mesh Graphormer, for
3d human pose
and
mesh reconstruction
from a single imag
→