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

TL;DR

This paper introduces PoseDA, an unsupervised domain adaptation framework that combines global position alignment and local pose augmentation to improve 3D human pose estimation across different datasets.

Contribution

It proposes a novel framework integrating global adaptation and local generalization without extra learnable parameters for better cross-dataset performance.

Findings

Achieves 61.3 mm MPJPE on MPI-INF-3DHP, surpassing previous methods by 10.2%.

Effectively reduces domain shift in 3D human pose estimation.

Enhances pose diversity through adversarial local pose augmentation.

Abstract

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 \textbf{global adaptation} and \textbf{local generalization} in \textit{PoseDA}, 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. \textit{PoseDA} 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\%.