Papers › Global Adaptation meets Local Generalization: Unsupervised Domain Adaptation for 3D...

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

29 Mar 2023ICCV 2023 1arXiv:2303.16456archive 2025-07-28

Wenhao Chai, Zhongyu Jiang, Jenq-Neng Hwang, Gaoang Wang

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\%.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

rese1f/PoseDA officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Human Pose Estimation3D Human Pose Estimation in Limited DataCross-domain 3D Human Pose EstimationDiversityDomain AdaptationPose EstimationUnsupervised Domain Adaptation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation MPI-INF-3DHP PoseDA AUC 62.5 #26 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP PoseDA MPJPE 61.3 #26 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP PoseDA PCK 92.1 #26 of 108 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ALIGN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections