EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VR
This work provides more accurate and temporally consistent egocentric human motion estimation, which is crucial for enhancing AR/VR experiences for users.
EgoPoseFormer v2 tackles egocentric human motion estimation for AR/VR, achieving a 12.2% and 19.4% accuracy improvement over state-of-the-art methods on the EgoBody3M benchmark, while reducing temporal jitter by 22.2% and 51.7%. Its auto-labeling system further boosts wrist MPJPE by 13.1%.
Egocentric human motion estimation is essential for AR/VR experiences, yet remains challenging due to limited body coverage from the egocentric viewpoint, frequent occlusions, and scarce labeled data. We present EgoPoseFormer v2, a method that addresses these challenges through two key contributions: (1) a transformer-based model for temporally consistent and spatially grounded body pose estimation, and (2) an auto-labeling system that enables the use of large unlabeled datasets for training. Our model is fully differentiable, introduces identity-conditioned queries, multi-view spatial refinement, causal temporal attention, and supports both keypoints and parametric body representations under a constant compute budget. The auto-labeling system scales learning to tens of millions of unlabeled frames via uncertainty-aware semi-supervised training. The system follows a teacher-student schema to generate pseudo-labels and guide training with uncertainty distillation, enabling the model to generalize to different environments. On the EgoBody3M benchmark, with a 0.8 ms latency on GPU, our model outperforms two state-of-the-art methods by 12.2% and 19.4% in accuracy, and reduces temporal jitter by 22.2% and 51.7%. Furthermore, our auto-labeling system further improves the wrist MPJPE by 13.1%.