Search Results for author:
Found 4 papers, 3 papers with code
WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion
We address these limitations with WHAM (World-grounded Humans with Accurate Motion), which accurately and efficiently reconstructs 3D human motion in a global coordinate system from video.
Ranked #1 on
3D Human Pose Estimation
on 3DPW
Markerless Motion Tracking with Noisy Video and IMU Data
We propose deep learning models to estimate human movement with noisy data from videos (VideoNet), inertial sensors (IMUNet), and a combination of the two (FusionNet), obviating the need for careful calibration.
Estimation of kinematics from inertial measurement units using a combined deep learning and optimization framework
Careful sensor-to-segment alignment and calibration strategies are also necessary, which may burden users and lead to further error in uncontrolled settings.
Multi-view Human Pose and Shape Estimation Using Learnable Volumetric Aggregation
In this paper, we propose a learnable volumetric aggregation approach to reconstruct 3D human body pose and shape from calibrated multi-view images.
