UC Riverside

The capability to accurately estimate 3D human poses is crucial for diverse fields such as action recognition and virtual/augmented reality. However, a persistent and significant challenge within this field is the accurate prediction of human poses under conditions of severe occlusion. Traditional image-based estimators struggle with heavy occlusions due to a lack of temporal context, resulting in inconsistent predictions. While video-based models benefit from processing temporal data, they encounter limitations when faced with prolonged occlusions that extend over multiple frames. Addressing these challenges, we propose STRIDE, a novel Test-Time Training (TTT) approach to fit a human motion prior for each video. This approach specifically handles occlusions that were not encountered during the model's training. We validate STRIDE's efficacy through comprehensive experiments on challenging datasets like Occluded Human3.6M, Human3.6M, and OCMotion, where it not only outperforms existing pose estimation models but also showcases superior handling of substantial occlusions, achieving fast and temporally consistent 3D pose estimates.