Abstract
We introduce a markerless approach to deform a quality human body template mesh from its original pose to a different pose specified by a point cloud. The point cloud may be noisy, incomplete, or even captured from a different person. In this approach, we first build coarse correspondences between the template mesh and the point cloud through a squeezed spectral embedding technique that exploits human body extremities. Based on these correspondences, we define the goal of non-rigid registration using an elastic energy functional and apply a discrete gradient flow to reduce the difference between a coarse control mesh and the point cloud. The deformed template mesh can then be obtained from the deformation of the control mesh using mean value coordinates afterwards. Our experiments show (see the supplementary video) that the approach is capable of equipping a mesh with the pose of a scanned point cloud data even if it is incomplete and noisy.
Huamin Wang
Chief Scientist
My research interests include physics-based simulation and modeling, generative AI, numerical analysis and nonlinear optimization.