# Absolute Human Pose Estimation with Depth Prediction Network

arXiv: https://arxiv.org/abs/1904.05947 · HTML: https://mlsanity.com/paper/1904.05947/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2019.

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

- [StyleGAN-Human: A Data-Centric Odyssey of Human Generation](https://mlsanity.com/paper/2204.11823/) (2022)
- [Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization](https://mlsanity.com/paper/2203.11471/) (2022)
- [Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR](https://mlsanity.com/paper/2211.16951/) (2022)
- [RT-Pose: A 4D Radar Tensor-based 3D Human Pose Estimation and Localization Benchmark](https://mlsanity.com/paper/2407.13930/) (2024)
- [VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data](https://mlsanity.com/paper/2207.09949/) (2022)
- [NIMBLE: A Non-rigid Hand Model with Bones and Muscles](https://mlsanity.com/paper/2202.04533/) (2022)
- [DepthFake: a depth-based strategy for detecting Deepfake videos](https://mlsanity.com/paper/2208.11074/) (2022)
- [FAKER: Full-body Anonymization with Human Keypoint Extraction for Real-time Video Deidentification](https://mlsanity.com/paper/2408.11829/) (2024)
- [Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation](https://mlsanity.com/paper/2207.07900/) (2022)

## Abstract (arXiv)

The common approach to 3D human pose estimation is predicting the body joint coordinates relative to the hip. This works well for a single person but is insufficient in the case of multiple interacting people. Methods predicting absolute coordinates first estimate a root-relative pose then calculate the translation via a secondary optimization task. We propose a neural network that predicts joints in a camera centered coordinate system instead of a root-relative one. Unlike previous methods, our network works in a single step without any post-processing. Our network beats previous methods on the MuPoTS-3D dataset and achieves state-of-the-art results.