Motion graphs for unstructured textured meshes

Motion graphs for unstructured textured meshes
Fabian Prada, Michael Kazhdan, Ming Chuang, Alvaro Collet, Hugues Hoppe.
ACM Trans. Graphics (SIGGRAPH), 35(4), 2016.
Automatic smooth transitions between similar meshes in a scanned sequence.
Abstract: Scanned performances are commonly represented in virtual environments as sequences of textured triangle meshes. Detailed shapes deforming over time benefit from meshes with dynamically evolving connectivity. We analyze these unstructured mesh sequences to automatically synthesize motion graphs with new smooth transitions between compatible poses and actions. Such motion graphs enable natural periodic motions, stochastic playback, and user-directed animations. The main challenge of unstructured sequences is that the meshes differ not only in connectivity but also in alignment, shape, and texture. We introduce new geometry processing techniques to address these problems and demonstrate visually seamless transitions on high-quality captures.
Hindsights: Although most of our data is captured at 30 frames/second, we find that it is easy to interpolate the geometry (in the GPU) to the native display rate (e.g. 90 fps) for the best experience in a virtual environment.