UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues

arXiv:2404.14634v1 Announce Type: new
Abstract: We introduce UPose3D, a novel approach for multi-view 3D human pose estimation, addressing challenges in accuracy and scalability. Our method advances existing pose estimation frameworks by improving robustness and flexibility without requiring direct 3D annotations. At the core of our method, a pose compiler module refines predictions from a 2D keypoints estimator that operates on a single image by leveraging temporal and cross-view information. Our novel cross-view fusion strategy is scalable to any number of …

abstract accuracy advances annotations arxiv challenges compiler core cs.cv flexibility frameworks human improving novel robustness scalability temporal type uncertainty view