Generalizable Human Pose Triangulation

We address the problem of generalizability for multi-view 3D human pose estimation. The standard approach is to first detect 2D keypoints in images and then apply triangulation from multiple views. Even though the existing methods achieve remarkably accurate 3D pose estimation on public benchmarks, most of them are limited to a single spatial camera arrangement and their number. Several methods address this limitation but demonstrate significantly degraded performance on novel views. We propose a stochastic framework for human pose triangulation and demonstrate a superior generalization across different camera arrangements on two public datasets. In addition, we apply the same approach to the fundamental matrix estimation problem, showing that the proposed method can successfully apply to other computer vision problems. The stochastic framework achieves more than 8.8% improvement on the 3D pose estimation task, compared to the state-of-the-art, and more than 30% improvement for fundamental matrix estimation, compared to a standard algorithm.

PDF Abstract CVPR 2022 PDF CVPR 2022 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Human Pose Estimation Human3.6M Generalizable Human Pose Triangulation Average MPJPE (mm) 29.1 # 32
Using 2D ground-truth joints No # 2
Multi-View or Monocular Multi-View # 1

Methods


No methods listed for this paper. Add relevant methods here