A Dual-Source Approach for 3D Pose Estimation from a Single Image

TL;DR

This paper introduces a dual-source method for 3D pose estimation from a single image, combining 2D annotated images and 3D motion capture data to overcome training data limitations.

Contribution

It proposes a novel dual-source approach that integrates 2D pose estimation with 3D pose retrieval, enabling effective 3D pose estimation from limited data.

Findings

Achieves state-of-the-art results in 3D pose estimation.

Performs well even with differing skeleton structures.

Demonstrates robustness and efficiency in the proposed method.

Abstract

One major challenge for 3D pose estimation from a single RGB image is the acquisition of sufficient training data. In particular, collecting large amounts of training data that contain unconstrained images and are annotated with accurate 3D poses is infeasible. We therefore propose to use two independent training sources. The first source consists of images with annotated 2D poses and the second source consists of accurate 3D motion capture data. To integrate both sources, we propose a dual-source approach that combines 2D pose estimation with efficient and robust 3D pose retrieval. In our experiments, we show that our approach achieves state-of-the-art results and is even competitive when the skeleton structure of the two sources differ substantially.