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

17 Mar 2024  ·  Qucheng Peng, Ce Zheng, Chen Chen ·

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 \url{https://github.com/davidpengucf/DAF-DG}.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Weakly-supervised 3D Human Pose Estimation Human3.6M DAF-DG-27frames Average MPJPE (mm) 44.1 # 2
Number of Views 1 # 1
Number of Frames Per View 27 # 10
3D Annotations S1 # 1
Weakly-supervised 3D Human Pose Estimation Human3.6M DAF-DG Average MPJPE (mm) 50.3 # 4
Number of Views 1 # 1
Number of Frames Per View 1 # 1
3D Annotations S1 # 1

Methods


No methods listed for this paper. Add relevant methods here