# Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation

arXiv: https://arxiv.org/abs/2306.17074 · HTML: https://mlsanity.com/paper/2306.17074/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 48 of its 55 references that are in the map.
- First posted on arXiv 29 Jun 2023.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 48)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures](https://mlsanity.com/paper/2211.07600/) (2022)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.14951/) (2021)
- [Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning](https://mlsanity.com/paper/2208.04202/) (2022)
- [DiffusionDet: Diffusion Model for Object Detection](https://mlsanity.com/paper/2211.09788/) (2022)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation](https://mlsanity.com/paper/1908.10357/) (2019)
- [CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark](https://mlsanity.com/paper/1812.00324/) (2018)
- [DeepHuman: 3D Human Reconstruction from a Single Image](https://mlsanity.com/paper/1903.06473/) (2019)
- [DaViT: Dual Attention Vision Transformers](https://mlsanity.com/paper/2204.03645/) (2022)
- [Distribution-Aware Coordinate Representation for Human Pose Estimation](https://mlsanity.com/paper/1910.06278/) (2019)
- [H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motion](https://mlsanity.com/paper/2110.13746/) (2021)
- [HRFormer: High-Resolution Transformer for Dense Prediction](https://mlsanity.com/paper/2110.09408/) (2021)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [TransPose: Keypoint Localization via Transformer](https://mlsanity.com/paper/2012.14214/) (2020)
- [Compositional Human Pose Regression](https://mlsanity.com/paper/1704.00159/) (2017)

## Built on by (most cited first, 5 of 5)

- [Diffusion Model is a Good Pose Estimator from 3D RF-Vision](https://mlsanity.com/paper/2403.16198/) (2024)
- [DPoser: Diffusion Model as Robust 3D Human Pose Prior](https://mlsanity.com/paper/2312.05541/) (2023)
- [FurniScene: A Large-scale 3D Room Dataset with Intricate Furnishing Scenes](https://mlsanity.com/paper/2401.03470/) (2024)
- [Guided Diffusion from Self-Supervised Diffusion Features](https://mlsanity.com/paper/2312.08825/) (2023)
- [Refinement Module based on Parse Graph for Human Pose Estimation](https://mlsanity.com/paper/2501.11069/) (2025)

## Abstract (arXiv)

One of the mainstream schemes for 2D human pose estimation (HPE) is learning keypoints heatmaps by a neural network. Existing methods typically improve the quality of heatmaps by customized architectures, such as high-resolution representation and vision Transformers. In this paper, we propose DiffusionPose, a new scheme that formulates 2D HPE as a keypoints heatmaps generation problem from noised heatmaps. During training, the keypoints are diffused to random distribution by adding noises and the diffusion model learns to recover ground-truth heatmaps from noised heatmaps with respect to conditions constructed by image feature. During inference, the diffusion model generates heatmaps from initialized heatmaps in a progressive denoising way. Moreover, we further explore improving the performance of DiffusionPose with conditions from human structural information. Extensive experiments show the prowess of our DiffusionPose, with improvements of 1.6, 1.2, and 1.2 mAP on widely-used COCO, CrowdPose, and AI Challenge datasets, respectively.