Search Results for author:
Found 2 papers, 0 papers with code
UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues
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.
SkelFormer: Markerless 3D Pose and Shape Estimation using Skeletal Transformers
Next, we design a regression-based inverse-kinematic skeletal transformer that maps the joint positions to pose and shape representations from heavily noisy observations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
