Video-driven Animation of Human Body Scans

We present a versatile, fast and simple framework to generate animations of scanned human characters from input multiview 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.
Author(s): | Edilson de Aguiar, Rhaleb Zayer, Christian Theobalt, Marcus Magnor, Hans-Peter Seidel |
---|---|
Published: | May 2007 |
Type: | Article in conference proceedings |
Book: | Proc. 3D Data Processing, Visualization and Transmission (3DPVT) |
Presented at: | 3D Data Processing, Visualization and Transmission (3DPVT) |
@inproceedings{aguiar2007body, title = {Video-driven Animation of Human Body Scans}, author = {de Aguiar, Edilson and Zayer, Rhaleb and Theobalt, Christian and Magnor, Marcus and Seidel, Hans-Peter}, booktitle = {Proc. 3D Data Processing, Visualization and Transmission (3{DPVT})}, month = {May}, year = {2007} }
Authors
Edilson de Aguiar
ExternalRhaleb Zayer
ExternalChristian Theobalt
ExternalMarcus Magnor
Director, ChairHans-Peter Seidel
External