WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation

TL;DR

WorldPose is a comprehensive new dataset from the 2022 FIFA World Cup that enables advanced research in multi-person 3D global pose estimation in outdoor, real-world sports environments, with extensive annotations and camera data.

Contribution

The paper introduces WorldPose, a large-scale, multi-view dataset with accurate 3D pose annotations from a major sporting event, enabling new research in global pose estimation.

Findings

Existing methods struggle with the complexity of the dataset.

WorldPose reveals limitations of current multi-person pose estimation techniques.

The dataset supports development of more robust global pose estimation algorithms.

Abstract

We present WorldPose, a novel dataset for advancing research in multi-person global pose estimation in the wild, featuring footage from the 2022 FIFA World Cup. While previous datasets have primarily focused on local poses, often limited to a single person or in constrained, indoor settings, the infrastructure deployed for this sporting event allows access to multiple fixed and moving cameras in different stadiums. We exploit the static multi-view setup of HD cameras to recover the 3D player poses and motions with unprecedented accuracy given capture areas of more than 1.75 acres. We then leverage the captured players' motions and field markings to calibrate a moving broadcasting camera. The resulting dataset comprises more than 80 sequences with approx 2.5 million 3D poses and a total traveling distance of over 120 km. Subsequently, we conduct an in-depth analysis of the SOTA methods for global pose estimation. Our experiments demonstrate that WorldPose challenges existing multi-person techniques, supporting the potential for new research in this area and others, such as sports analysis. All pose annotations (in SMPL format), broadcasting camera parameters and footage will be released for academic research purposes.