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

Qucheng Peng, Ce Zheng, Chen Chen; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 2240-2249

Abstract


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.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Peng_2024_CVPR, author = {Peng, Qucheng and Zheng, Ce and Chen, Chen}, title = {A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2240-2249} }