Generalizable Human Pose Triangulation

TL;DR

This paper introduces a stochastic framework for multi-view 3D human pose estimation that significantly improves generalization across different camera setups and also enhances fundamental matrix estimation accuracy.

Contribution

The paper presents a novel stochastic approach that outperforms existing methods in generalizing 3D human pose triangulation to new camera arrangements and applies successfully to fundamental matrix estimation.

Findings

Over 8.8% improvement in 3D pose estimation accuracy.

More than 30% enhancement in fundamental matrix estimation.

Superior generalization across diverse camera configurations.

Abstract

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.