We present a versatile, fast and simple framework to generate animations of scanned human characters from input multi-view video sequences. Our method is purely mesh-based and requires only a minimum of manual interaction. The proposed algorithm implicitly generates realistic body deformations and can easily transfer motions between human subjects of completely different shape and proportions. We feature a working prototype system that demonstrates that our method can generate convincing lifelike character animations from marker-less optical motion capture data.
展开▼