3D Human Pose Estimation with Spatial and Temporal Transformers

by   chen chen, et al.

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



There are no comments yet.


page 7

page 8

page 12

page 14

page 15


PE-former: Pose Estimation Transformer

Vision transformer architectures have been demonstrated to work very eff...

Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation

3D human shape and pose estimation is the essential task for human motio...

A Spatial-temporal 3D Human Pose Reconstruction Framework

3D human pose reconstruction from single-view camera is a difficult and ...

GraFormer: Graph Convolution Transformer for 3D Pose Estimation

Exploiting relations among 2D joints plays a crucial role yet remains se...

Swin-Pose: Swin Transformer Based Human Pose Estimation

Convolutional neural networks (CNNs) have been widely utilized in many c...

MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

Estimating 3D human poses from monocular videos is a challenging task du...

Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos

Graph Convolution Network (GCN) has been successfully used for 3D human ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.