# Single-Network Whole-Body Pose Estimation

arXiv: https://arxiv.org/abs/1909.13423 · HTML: https://mlsanity.com/paper/1909.13423/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2019.

## Built on by (most cited first, 24 of 24)

- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)
- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [Capturing and Inferring Dense Full-Body Human-Scene Contact](https://mlsanity.com/paper/2206.09553/) (2022)
- [RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose](https://mlsanity.com/paper/2303.07399/) (2023)
- [Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer](https://mlsanity.com/paper/2204.08680/) (2022)
- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [Content4All Open Research Sign Language Translation Datasets](https://mlsanity.com/paper/2105.02351/) (2021)
- [Evaluating the Immediate Applicability of Pose Estimation for Sign Language Recognition](https://mlsanity.com/paper/2104.10166/) (2021)
- [ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild](https://mlsanity.com/paper/2208.11547/) (2022)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [TCFormer: Visual Recognition via Token Clustering Transformer](https://mlsanity.com/paper/2407.11321/) (2024)
- [HHP-Net: A light Heteroscedastic neural network for Head Pose estimation with uncertainty](https://mlsanity.com/paper/2111.01440/) (2021)
- [NIMBLE: A Non-rigid Hand Model with Bones and Muscles](https://mlsanity.com/paper/2202.04533/) (2022)
- [GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation](https://mlsanity.com/paper/2407.10756/) (2024)
- [Capturing Detailed Deformations of Moving Human Bodies](https://mlsanity.com/paper/2102.07343/) (2021)
- [Expressive Forecasting of 3D Whole-body Human Motions](https://mlsanity.com/paper/2312.11972/) (2023)
- [Template-Free Try-on Image Synthesis via Semantic-guided Optimization](https://mlsanity.com/paper/2102.03503/) (2021)
- [SpineOne: A One-Stage Detection Framework for Degenerative Discs and Vertebrae](https://mlsanity.com/paper/2110.15082/) (2021)
- [Towards Fine-Grained Human Motion Video Captioning](https://mlsanity.com/paper/2510.24767/) (2025)
- [HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation](https://mlsanity.com/paper/2106.04269/) (2021)
- [Can AI detect pain and express pain empathy? A review from emotion recognition and a human-centered AI perspective](https://mlsanity.com/paper/2110.04249/) (2021)
- [WiCompass: Oracle-driven Data Scaling for mmWave Human Pose Estimation](https://mlsanity.com/paper/2602.18726/) (2026)
- [CIGPose: Causal Intervention Graph Neural Network for Whole-Body Pose Estimation](https://mlsanity.com/paper/2603.09418/) (2026)
- [Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation](https://mlsanity.com/paper/2207.07900/) (2022)

## Abstract (arXiv)

We present the first single-network approach for 2D~whole-body pose estimation, which entails simultaneous localization of body, face, hands, and feet keypoints. Due to the bottom-up formulation, our method maintains constant real-time performance regardless of the number of people in the image. The network is trained in a single stage using multi-task learning, through an improved architecture which can handle scale differences between body/foot and face/hand keypoints. Our approach considerably improves upon OpenPose~citecao2018openpose, the only work so far capable of whole-body pose estimation, both in terms of speed and global accuracy. Unlike OpenPose, our method does not need to run an additional network for each hand and face candidate, making it substantially faster for multi-person scenarios. This work directly results in a reduction of computational complexity for applications that require 2D whole-body information (e.g., VR/AR, re-targeting). In addition, it yields higher accuracy, especially for occluded, blurry, and low resolution faces and hands. For code, trained models, and validation benchmarks, visit our project page: https://github.com/CMU-Perceptual-Computing-Lab/openposetrain.