Robust Monocular 3D Human Motion With Lasso-Based Differential Kinematics

Abed Malti; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 6608-6618

This work introduces a method to robustly reconstruct 3D human motion from the motion of 2D skeletal landmarks. We propose to use a lasso (least absolute shrinkage and selection operator) optimization framework where the l1-norm is computed over the vector of differential angular kinematics and the l2-norm is computed over the differential 2D reprojection error. The l1-norm term allows us to model sparse kinematic angular motion. The minimization of the reprojection error allows us to assume a bounded noise in both the kinematic model and the 2D landmark detection. This bound is controlled by a scale factor associated to the l2-norm data term. A posteriori verification condition is provided to check whether or not the lasso formulation has allowed us to recover the ground-truth 3D human motion. Results on publicly available data demonstrates the effectiveness of the proposed approach on state-of-the-art methods. It shows that both sparsity and bounded noise assumptions encoded in lasso formulation are robust priors to safely recover 3D human motion.