# Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation

arXiv: https://arxiv.org/abs/2303.11579 · HTML: https://mlsanity.com/paper/2303.11579/

## Key facts

- Cited by 82 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 72 references that are in the map.
- First posted on arXiv 21 Mar 2023.

## Builds on (most cited first, 30 of 54)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [DiGress: Discrete Denoising diffusion for graph generation](https://mlsanity.com/paper/2209.14734/) (2022)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [3D human pose estimation in video with temporal convolutions and semi-supervised training](https://mlsanity.com/paper/1811.11742/) (2018)
- [A simple yet effective baseline for 3d human pose estimation](https://mlsanity.com/paper/1705.03098/) (2017)
- [DiffusionDet: Diffusion Model for Object Detection](https://mlsanity.com/paper/2211.09788/) (2022)
- [Cascaded Pyramid Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/1711.07319/) (2017)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations](https://mlsanity.com/paper/2202.02514/) (2022)
- [3D Human Pose Estimation with Spatial and Temporal Transformers](https://mlsanity.com/paper/2103.10455/) (2021)
- [Permutation Invariant Graph Generation via Score-Based Generative Modeling](https://mlsanity.com/paper/2003.00638/) (2020)
- [Conditional Image Generation with Score-Based Diffusion Models](https://mlsanity.com/paper/2111.13606/) (2021)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2111.12707/) (2021)
- [ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech](https://mlsanity.com/paper/2207.06389/) (2022)

## Built on by (most cited first, 30 of 82)

- [MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusion](https://mlsanity.com/paper/2310.14729/) (2023)
- [KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2404.00658/) (2024)
- [Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement](https://mlsanity.com/paper/2311.16495/) (2023)
- [Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning](https://mlsanity.com/paper/2404.05218/) (2024)
- [SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generation](https://mlsanity.com/paper/2307.01646/) (2023)
- [FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models](https://mlsanity.com/paper/2405.05216/) (2024)
- [Diffusion Model is a Good Pose Estimator from 3D RF-Vision](https://mlsanity.com/paper/2403.16198/) (2024)
- [ExpertAF: Expert Actionable Feedback from Video](https://mlsanity.com/paper/2408.00672/) (2024)
- [Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observation](https://mlsanity.com/paper/2411.16810/) (2024)
- [Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Models](https://mlsanity.com/paper/2308.02963/) (2023)
- [AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements](https://mlsanity.com/paper/2503.07499/) (2025)
- [Attention-Propagation Network for Egocentric Heatmap to 3D Pose Lifting](https://mlsanity.com/paper/2402.18330/) (2024)
- [Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser](https://mlsanity.com/paper/2403.04444/) (2024)
- [DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans](https://mlsanity.com/paper/2404.00485/) (2024)
- [PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimation](https://mlsanity.com/paper/2308.09678/) (2023)
- [HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud](https://mlsanity.com/paper/2404.03159/) (2024)
- [Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2407.13642/) (2024)
- [Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network](https://mlsanity.com/paper/2408.02922/) (2024)
- [Action Detection via an Image Diffusion Process](https://mlsanity.com/paper/2404.01051/) (2024)
- [EnvPoser: Environment-aware Realistic Human Motion Estimation from Sparse Observations with Uncertainty Modeling](https://mlsanity.com/paper/2412.10235/) (2024)
- [DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion](https://mlsanity.com/paper/2309.01575/) (2023)
- [HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimation](https://mlsanity.com/paper/2503.23331/) (2025)
- [Unsupervised 3D Pose Estimation with Non-Rigid Structure-from-Motion Modeling](https://mlsanity.com/paper/2308.10705/) (2023)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation](https://mlsanity.com/paper/2312.06386/) (2023)
- [GazeHTA: End-to-end Gaze Target Detection with Head-Target Association](https://mlsanity.com/paper/2404.10718/) (2024)
- [DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recovery](https://mlsanity.com/paper/2504.03006/) (2025)
- [CHAMP: Conformalized 3D Human Multi-Hypothesis Pose Estimators](https://mlsanity.com/paper/2407.06141/) (2024)
- [Linguistics-Vision Monotonic Consistent Network for Sign Language Production](https://mlsanity.com/paper/2412.16944/) (2024)
- [Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Models](https://mlsanity.com/paper/2503.19914/) (2025)

## Abstract (arXiv)

In this paper, a novel Diffusion-based 3D Pose estimation (D3DP) method with Joint-wise reProjection-based Multi-hypothesis Aggregation (JPMA) is proposed for probabilistic 3D human pose estimation. On the one hand, D3DP generates multiple possible 3D pose hypotheses for a single 2D observation. It gradually diffuses the ground truth 3D poses to a random distribution, and learns a denoiser conditioned on 2D keypoints to recover the uncontaminated 3D poses. The proposed D3DP is compatible with existing 3D pose estimators and supports users to balance efficiency and accuracy during inference through two customizable parameters. On the other hand, JPMA is proposed to assemble multiple hypotheses generated by D3DP into a single 3D pose for practical use. It reprojects 3D pose hypotheses to the 2D camera plane, selects the best hypothesis joint-by-joint based on the reprojection errors, and combines the selected joints into the final pose. The proposed JPMA conducts aggregation at the joint level and makes use of the 2D prior information, both of which have been overlooked by previous approaches. Extensive experiments on Human3.6M and MPI-INF-3DHP datasets show that our method outperforms the state-of-the-art deterministic and probabilistic approaches by 1.5% and 8.9%, respectively. Code is available at https://github.com/paTRICK-swk/D3DP.