Cross-domain 3D Human Pose Estimation

1 papers with code • 2 benchmarks • 2 datasets

This task has no description! Would you like to contribute one?

Most implemented papers

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

rese1f/PoseDA ICCV 2023

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.