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

arXiv: https://arxiv.org/abs/1509.06720 · HTML: https://mlsanity.com/paper/1509.06720/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Sep 2015.

## Built on by (most cited first, 9 of 9)

- [HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery](https://mlsanity.com/paper/2304.05690/) (2023)
- [D&D: Learning Human Dynamics from Dynamic Camera](https://mlsanity.com/paper/2209.08790/) (2022)
- [A Survey on Human-aware Robot Navigation](https://mlsanity.com/paper/2106.11650/) (2021)
- [Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos](https://mlsanity.com/paper/2109.07353/) (2021)
- [MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation](https://mlsanity.com/paper/2509.00649/) (2025)
- [Deep Monocular 3D Human Pose Estimation via Cascaded Dimension-Lifting](https://mlsanity.com/paper/2104.03520/) (2021)
- [On the role of depth predictions for 3D human pose estimation](https://mlsanity.com/paper/2103.02521/) (2021)
- [Adapted Human Pose: Monocular 3D Human Pose Estimation with Zero Real 3D Pose Data](https://mlsanity.com/paper/2105.10837/) (2021)
- [Augmenting Vision-Based Human Pose Estimation with Rotation Matrix](https://mlsanity.com/paper/2310.06068/) (2023)

## Abstract (arXiv)

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.