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

arXiv: https://arxiv.org/abs/1705.02883 · HTML: https://mlsanity.com/paper/1705.02883/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2017.

## Built on by (most cited first, 7 of 7)

- [Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentation](https://mlsanity.com/paper/2107.00434/) (2021)
- [Fusion-GCN: Multimodal Action Recognition using Graph Convolutional Networks](https://mlsanity.com/paper/2109.12946/) (2021)
- [A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/2304.03635/) (2023)
- [Everybody Is Unique: Towards Unbiased Human Mesh Recovery](https://mlsanity.com/paper/2107.06239/) (2021)
- [Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry](https://mlsanity.com/paper/2108.07777/) (2021)
- [Iterative Greedy Matching for 3D Human Pose Tracking from Multiple Views](https://mlsanity.com/paper/2101.09745/) (2021)
- [Self-Supervised 3D Human Pose Estimation in Static Video Via Neural Rendering](https://mlsanity.com/paper/2210.04514/) (2022)

## Abstract (arXiv)

In this work we address the challenging problem of 3D human pose estimation from single images. Recent approaches learn deep neural networks to regress 3D pose directly from images. One major challenge for such methods, however, is the collection of training data. Specifically, collecting large amounts of training data containing unconstrained images annotated with accurate 3D poses is infeasible. We therefore propose to use two independent training sources. The first source consists of accurate 3D motion capture data, and the second source consists of unconstrained images with annotated 2D poses. To integrate both sources, we propose a dual-source approach that combines 2D pose estimation with efficient 3D pose retrieval. To this end, we first convert the motion capture data into a normalized 2D pose space, and separately learn a 2D pose estimation model from the image data. During inference, we estimate the 2D pose and efficiently retrieve the nearest 3D poses. We then jointly estimate a mapping from the 3D pose space to the image and reconstruct the 3D pose. We provide a comprehensive evaluation of the proposed method and experimentally demonstrate the effectiveness of our approach, even when the skeleton structures of the two sources differ substantially.