# Global Adaptation meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation

arXiv: https://arxiv.org/abs/2303.16456 · HTML: https://mlsanity.com/paper/2303.16456/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 67 references that are in the map.
- First posted on arXiv 29 Mar 2023.

## Builds on (most cited first, 30 of 47)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [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)
- [A Survey of Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1812.02849/) (2018)
- [Learning from Synthetic Humans](https://mlsanity.com/paper/1701.01370/) (2017)
- [Cascaded Pyramid Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/1711.07319/) (2017)
- [Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks](https://mlsanity.com/paper/1612.05424/) (2016)
- [Mesh Graphormer](https://mlsanity.com/paper/2104.00272/) (2021)
- [Semantic Graph Convolutional Networks for 3D Human Pose Regression](https://mlsanity.com/paper/1904.03345/) (2019)
- [Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB](https://mlsanity.com/paper/1712.03453/) (2017)
- [PoseTrack: A Benchmark for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1710.10000/) (2017)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera](https://mlsanity.com/paper/1705.01583/) (2017)
- [3D Human Pose Estimation = 2D Pose Estimation + Matching](https://mlsanity.com/paper/1612.06524/) (2016)
- [Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation](https://mlsanity.com/paper/2004.03686/) (2020)
- [Unsupervised 3D Pose Estimation with Geometric Self-Supervision](https://mlsanity.com/paper/1904.04812/) (2019)
- [SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach](https://mlsanity.com/paper/2007.09389/) (2020)
- [PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation](https://mlsanity.com/paper/2105.02465/) (2021)
- [Pose-driven Deep Convolutional Model for Person Re-identification](https://mlsanity.com/paper/1709.08325/) (2017)
- [3D Human Pose Estimation in the Wild by Adversarial Learning](https://mlsanity.com/paper/1803.09722/) (2018)
- [RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation](https://mlsanity.com/paper/1902.09868/) (2019)
- [Cascaded deep monocular 3D human pose estimation with evolutionary training data](https://mlsanity.com/paper/2006.07778/) (2020)
- [EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation](https://mlsanity.com/paper/2303.12787/) (2023)
- [Synthesizing Training Images for Boosting Human 3D Pose Estimation](https://mlsanity.com/paper/1604.02703/) (2016)

## Built on by (most cited first, 19 of 19)

- [Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning](https://mlsanity.com/paper/2404.05218/) (2024)
- [Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation](https://mlsanity.com/paper/2307.03833/) (2023)
- [RT-Pose: A 4D Radar Tensor-based 3D Human Pose Estimation and Localization Benchmark](https://mlsanity.com/paper/2407.13930/) (2024)
- [A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation](https://mlsanity.com/paper/2403.11310/) (2024)
- [PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimation](https://mlsanity.com/paper/2308.09678/) (2023)
- [A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision](https://mlsanity.com/paper/2307.03353/) (2023)
- [MambaMOT: State-Space Model as Motion Predictor for Multi-Object Tracking](https://mlsanity.com/paper/2403.10826/) (2024)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [MPM: A Unified 2D-3D Human Pose Representation via Masked Pose Modeling](https://mlsanity.com/paper/2306.17201/) (2023)
- [Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation](https://mlsanity.com/paper/2403.06164/) (2024)
- [Your Turn: At Home Turning Angle Estimation for Parkinson's Disease Severity Assessment](https://mlsanity.com/paper/2408.08182/) (2024)
- [UniHPE: Towards Unified Human Pose Estimation via Contrastive Learning](https://mlsanity.com/paper/2311.16477/) (2023)
- [Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimation](https://mlsanity.com/paper/2402.02339/) (2024)
- [Unsupervised Cross-Domain 3D Human Pose Estimation via Pseudo-Label-Guided Global Transforms](https://mlsanity.com/paper/2504.12699/) (2025)
- [DPOT: A DeepParticle method for Computation of Optimal Transport with convergence guarantee](https://mlsanity.com/paper/2506.23429/) (2025)
- [AugLift: Depth-Aware Input Reparameterization Improves Domain Generalization in 2D-to-3D Pose Lifting](https://mlsanity.com/paper/2508.07112/) (2025)
- [UniHPR: Unified Human Pose Representation via Singular Value Contrastive Learning](https://mlsanity.com/paper/2510.19078/) (2025)
- [Leveraging 2D Masked Reconstruction for Domain Adaptation of 3D Pose Estimation](https://mlsanity.com/paper/2501.08408/) (2025)
- [Toward Efficient Generalization in 3D Human Pose Estimation via a Canonical Domain Approach](https://mlsanity.com/paper/2501.16146/) (2025)

## Abstract (arXiv)

When applying a pre-trained 2D-to-3D human pose lifting model to a target unseen dataset, large performance degradation is commonly encountered due to domain shift issues. We observe that the degradation is caused by two factors: 1) the large distribution gap over global positions of poses between the source and target datasets due to variant camera parameters and settings, and 2) the deficient diversity of local structures of poses in training. To this end, we combine global adaptation and local generalization in textitPoseDA, a simple yet effective framework of unsupervised domain adaptation for 3D human pose estimation. Specifically, global adaptation aims to align global positions of poses from the source domain to the target domain with a proposed global position alignment (GPA) module. And local generalization is designed to enhance the diversity of 2D-3D pose mapping with a local pose augmentation (LPA) module. These modules bring significant performance improvement without introducing additional learnable parameters. In addition, we propose local pose augmentation (LPA) to enhance the diversity of 3D poses following an adversarial training scheme consisting of 1) a augmentation generator that generates the parameters of pre-defined pose transformations and 2) an anchor discriminator to ensure the reality and quality of the augmented data. Our approach can be applicable to almost all 2D-3D lifting models. textitPoseDA achieves 61.3 mm of MPJPE on MPI-INF-3DHP under a cross-dataset evaluation setup, improving upon the previous state-of-the-art method by 10.2%.