ScanMove: Motion Prediction and Transfer for Unregistered Body Meshes
This addresses the challenge of handling noisy, unregistered meshes in computer graphics and animation, though it appears incremental as it builds on existing motion prediction methods.
The paper tackles the problem of generating plausible deformations for unregistered body meshes, such as raw 3D scans, by proposing a rig-free, data-driven framework for motion prediction and transfer, achieving effectiveness and versatility in tasks like walking and running.
Unregistered surface meshes, especially raw 3D scans, present significant challenges for automatic computation of plausible deformations due to the lack of established point-wise correspondences and the presence of noise in the data. In this paper, we propose a new, rig-free, data-driven framework for motion prediction and transfer on such body meshes. Our method couples a robust motion embedding network with a learned per-vertex feature field to generate a spatio-temporal deformation field, which drives the mesh deformation. Extensive evaluations, including quantitative benchmarks and qualitative visuals on tasks such as walking and running, demonstrate the effectiveness and versatility of our approach on challenging unregistered meshes.