MetaPose: Fast 3D Pose from Multiple Views without 3D Supervision

In the era of deep learning, human pose estimation from multiple cameras with unknown calibration has received little attention to date. We show how to train a neural model to perform this task with high precision and minimal latency overhead. The proposed model takes into account joint location uncertainty due to occlusion from multiple views, and requires only 2D keypoint data for training. Our method outperforms both classical bundle adjustment and weakly-supervised monocular 3D baselines on the well-established Human3.6M dataset, as well as the more challenging in-the-wild Ski-Pose PTZ dataset.

PDF Abstract CVPR 2022 PDF CVPR 2022 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Weakly-supervised 3D Human Pose Estimation Human3.6M MetaPose (S1+S2/SS) Average MPJPE (mm) 56 # 4
3D Human Pose Estimation Human3.6M MetaPose (S1+S2) Average MPJPE (mm) 49 # 147
3D Human Pose Estimation SkiPose MetaPose (S1+S2) MPJPE 53 # 1
P-MPJPE 42 # 2
3D Human Pose Estimation SkiPose MetaPose (S1+IR) MPJPE 54 # 2
P-MPJPE 30 # 3

Methods


No methods listed for this paper. Add relevant methods here