Efficient 2D to Full 3D Human Pose Uplifting including Joint Rotations
This work addresses the need for accurate and fast biomechanical analysis in sports analytics, offering a novel method that is incremental but provides significant speed and accuracy gains.
The paper tackled the problem of efficiently estimating 3D human poses with joint rotations from 2D inputs, achieving state-of-the-art accuracy in rotation estimation, 150 times faster than inverse kinematics methods, and improved joint localization precision over Human Mesh Recovery models.
In sports analytics, accurately capturing both the 3D locations and rotations of body joints is essential for understanding an athlete's biomechanics. While Human Mesh Recovery (HMR) models can estimate joint rotations, they often exhibit lower accuracy in joint localization compared to 3D Human Pose Estimation (HPE) models. Recent work addressed this limitation by combining a 3D HPE model with inverse kinematics (IK) to estimate both joint locations and rotations. However, IK is computationally expensive. To overcome this, we propose a novel 2D-to-3D uplifting model that directly estimates 3D human poses, including joint rotations, in a single forward pass. We investigate multiple rotation representations, loss functions, and training strategies - both with and without access to ground truth rotations. Our models achieve state-of-the-art accuracy in rotation estimation, are 150 times faster than the IK-based approach, and surpass HMR models in joint localization precision.