Transformer architectures have become the model of choice in natural language
processing and are now being introduced into computer vision tasks such as
image classification, object detection, and semantic segmentation. However, in
the field of human pose estimation, convolutional architectures still remain
dominant. In this work, we present PoseFormer, a purely transformer-based
approach for 3D human pose estimation in videos without convolutional
architectures involved. Inspired by recent developments in vision transformers,
we design a spatial-temporal transformer structure to comprehensively model the
human joint relations within each frame as well as the temporal correlations
across frames, then output an accurate 3D human pose of the center frame. We
quantitatively and qualitatively evaluate our method on two popular and
standard benchmark datasets: Human3.6M and MPI-INF-3DHP. Extensive experiments
show that PoseFormer achieves state-of-the-art performance on both datasets.
Code is available at https://github.com/zczcwh/PoseFormer

本研究提出一种基于 transformer 的算法，能够在视频中实现 3D 人体姿态估计，通过对空间和时间进行变换，对每一帧中人体关节关系进行建模，并在中心帧上输出准确的 3D 人体姿态，该算法在 Human3.6M 和 MPI-INF-3DHP 数据集上实现了最先进的成果。