3D Human Pose Estimation with Spatial and Temporal Transformers

🤖 Plain-English Summary

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. Extensive experiments show that PoseFormer achieves advanced performance on both datasets.

🔑 Key Findings

• 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.

🔗 Related Resources