# A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation

arXiv: https://arxiv.org/abs/2403.11310 · HTML: https://mlsanity.com/paper/2403.11310/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 15 references that are in the map.
- First posted on arXiv 17 Mar 2024.

## Builds on (most cited first, 11 of 11)

- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [3D human pose estimation in video with temporal convolutions and semi-supervised training](https://mlsanity.com/paper/1811.11742/) (2018)
- [Cascaded Pyramid Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/1711.07319/) (2017)
- [3D Human Pose Estimation with Spatial and Temporal Transformers](https://mlsanity.com/paper/2103.10455/) (2021)
- [Semantic Graph Convolutional Networks for 3D Human Pose Regression](https://mlsanity.com/paper/1904.03345/) (2019)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation](https://mlsanity.com/paper/2105.02465/) (2021)
- [AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation](https://mlsanity.com/paper/2112.11593/) (2021)
- [Global Adaptation meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation](https://mlsanity.com/paper/2303.16456/) (2023)
- [PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimation](https://mlsanity.com/paper/2308.09678/) (2023)
- [DH-AUG: DH Forward Kinematics Model Driven Augmentation for 3D Human Pose Estimation](https://mlsanity.com/paper/2207.09303/) (2022)

## Built on by (most cited first, 15 of 15)

- [Automatic News Generation and Fact-Checking System Based on Language Processing](https://mlsanity.com/paper/2405.10492/) (2024)
- [Optimizing Automated Picking Systems in Warehouse Robots Using Machine Learning](https://mlsanity.com/paper/2408.16633/) (2024)
- [Robust Domain Generalization for Multi-modal Object Recognition](https://mlsanity.com/paper/2408.05831/) (2024)
- [The application of Augmented Reality (AR) in Remote Work and Education](https://mlsanity.com/paper/2404.10579/) (2024)
- [Human-Centric Video Anomaly Detection Through Spatio-Temporal Pose Tokenization and Transformer](https://mlsanity.com/paper/2408.15185/) (2024)
- [Motion Capture from Inertial and Vision Sensors](https://mlsanity.com/paper/2407.16341/) (2024)
- [Emotion Recognition from Skeleton Data: A Comprehensive Survey](https://mlsanity.com/paper/2507.18026/) (2025)
- [FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation](https://mlsanity.com/paper/2512.14162/) (2025)
- [MuPPet: Multi-person 2D-to-3D Pose Lifting](https://mlsanity.com/paper/2604.09715/) (2026)
- [Unsupervised Cross-Domain 3D Human Pose Estimation via Pseudo-Label-Guided Global Transforms](https://mlsanity.com/paper/2504.12699/) (2025)
- [AugLift: Depth-Aware Input Reparameterization Improves Domain Generalization in 2D-to-3D Pose Lifting](https://mlsanity.com/paper/2508.07112/) (2025)
- [Cross-Sample Relational Fusion: Unifying Domain Generalization and Class-Incremental Learning](https://mlsanity.com/paper/2605.08839/) (2026)
- [Toward Efficient Generalization in 3D Human Pose Estimation via a Canonical Domain Approach](https://mlsanity.com/paper/2501.16146/) (2025)
- [SARS: A Novel Face and Body Shape and Appearance Aware 3D Reconstruction System extends Morphable Models](https://mlsanity.com/paper/2602.09918/) (2026)
- [Enhancing Domain Generalization in 3D Human Pose Estimation through Controllable Generative Augmentation](https://mlsanity.com/paper/2605.12198/) (2026)

## Abstract (arXiv)

3D human pose data collected in controlled laboratory settings present challenges for pose estimators that generalize across diverse scenarios. To address this, domain generalization is employed. Current methodologies in domain generalization for 3D human pose estimation typically utilize adversarial training to generate synthetic poses for training. Nonetheless, these approaches exhibit several limitations. First, the lack of prior information about the target domain complicates the application of suitable augmentation through a single pose augmentor, affecting generalization on target domains. Moreover, adversarial training's discriminator tends to enforce similarity between source and synthesized poses, impeding the exploration of out-of-source distributions. Furthermore, the pose estimator's optimization is not exposed to domain shifts, limiting its overall generalization ability. To address these limitations, we propose a novel framework featuring two pose augmentors: the weak and the strong augmentors. Our framework employs differential strategies for generation and discrimination processes, facilitating the preservation of knowledge related to source poses and the exploration of out-of-source distributions without prior information about target poses. Besides, we leverage meta-optimization to simulate domain shifts in the optimization process of the pose estimator, thereby improving its generalization ability. Our proposed approach significantly outperforms existing methods, as demonstrated through comprehensive experiments on various benchmark datasets.Our code will be released at urlhttps://github.com/davidpengucf/DAF-DG.