# Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement

arXiv: https://arxiv.org/abs/2007.10599 · HTML: https://mlsanity.com/paper/2007.10599/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jul 2020.

## Built on by (most cited first, 30 of 33)

- [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021)
- [Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future](https://mlsanity.com/paper/2105.13137/) (2021)
- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [Human Pose as Compositional Tokens](https://mlsanity.com/paper/2303.11638/) (2023)
- [HuPR: A Benchmark for Human Pose Estimation Using Millimeter Wave Radar](https://mlsanity.com/paper/2210.12564/) (2022)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation](https://mlsanity.com/paper/2110.05132/) (2021)
- [Low-resolution Human Pose Estimation](https://mlsanity.com/paper/2109.09090/) (2021)
- [Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation](https://mlsanity.com/paper/2208.00090/) (2022)
- [Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimation](https://mlsanity.com/paper/2208.03704/) (2022)
- [VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation](https://mlsanity.com/paper/2210.06028/) (2022)
- [Relation-Based Associative Joint Location for Human Pose Estimation in Videos](https://mlsanity.com/paper/2107.03591/) (2021)
- [Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation](https://mlsanity.com/paper/2303.11180/) (2023)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation](https://mlsanity.com/paper/2306.17074/) (2023)
- [Graph learning in robotics: a survey](https://mlsanity.com/paper/2310.04294/) (2023)
- [ProbRadarM3F: mmWave Radar based Human Skeletal Pose Estimation with Probability Map Guided Multi-Format Feature Fusion](https://mlsanity.com/paper/2405.05164/) (2024)
- [Single Person Pose Estimation: A Survey](https://mlsanity.com/paper/2109.10056/) (2021)
- [Category-Agnostic 6D Pose Estimation with Conditional Neural Processes](https://mlsanity.com/paper/2206.07162/) (2022)
- [Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation](https://mlsanity.com/paper/2207.02425/) (2022)
- [Human Modelling and Pose Estimation Overview](https://mlsanity.com/paper/2406.19290/) (2024)
- [DPIT: Dual-Pipeline Integrated Transformer for Human Pose Estimation](https://mlsanity.com/paper/2209.02431/) (2022)
- [Edge Graph Intelligence: Reciprocally Empowering Edge Networks with Graph Intelligence](https://mlsanity.com/paper/2407.15320/) (2024)
- [Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approach](https://mlsanity.com/paper/2409.02715/) (2024)
- [Direct Dense Pose Estimation](https://mlsanity.com/paper/2204.01263/) (2022)
- [GoalieNet: A Multi-Stage Network for Joint Goalie, Equipment, and Net Pose Estimation in Ice Hockey](https://mlsanity.com/paper/2306.15853/) (2023)
- [Measurement of Medial Elbow Joint Space using Landmark Detection](https://mlsanity.com/paper/2412.13010/) (2024)
- [VISUALCENT: Visual Human Analysis using Dynamic Centroid Representation](https://mlsanity.com/paper/2504.19032/) (2025)
- [CIGPose: Causal Intervention Graph Neural Network for Whole-Body Pose Estimation](https://mlsanity.com/paper/2603.09418/) (2026)
- [D3PRefiner: A Diffusion-based Denoise Method for 3D Human Pose Refinement](https://mlsanity.com/paper/2401.03914/) (2024)

## Abstract (arXiv)

Recently, most of the state-of-the-art human pose estimation methods are based on heatmap regression. The final coordinates of keypoints are obtained by decoding heatmap directly. In this paper, we aim to find a better approach to get more accurate localization results. We mainly put forward two suggestions for improvement: 1) different features and methods should be applied for rough and accurate localization, 2) relationship between keypoints should be considered. Specifically, we propose a two-stage graph-based and model-agnostic framework, called Graph-PCNN, with a localization subnet and a graph pose refinement module added onto the original heatmap regression network. In the first stage, heatmap regression network is applied to obtain a rough localization result, and a set of proposal keypoints, called guided points, are sampled. In the second stage, for each guided point, different visual feature is extracted by the localization subnet. The relationship between guided points is explored by the graph pose refinement module to get more accurate localization results. Experiments show that Graph-PCNN can be used in various backbones to boost the performance by a large margin. Without bells and whistles, our best model can achieve a new state-of-the-art 76.8% AP on COCO test-dev split.