Computer Graphics
TU Braunschweig

Multi-View Video Capture of Garment Motion


Multi-View Video Capture of Garment Motion

We present an image-based algorithm for surface reconstruction of moving garments from multiple calibrated video cameras. Using a color-coded cloth texture, we reliably match circular features between different camera views. As surface model we use an a priori known triangle mesh. By identifying the mesh vertices with texture elements we obtain a coherent parametrization of the surface over time without further processing. Missing data points resulting from self-shadowing are plausibly interpolated by minimizing a thin-plate functional. The deforming geometry can be used for different graphics

applications, e.g. for realistic retexturing.We show results for real garments demonstrating the accuracy of the recovered flexible shape.


Author(s):Volker Scholz, Marcus Magnor
Published:June 2006
Type:Article in conference proceedings
Book:Proc. IEEE Workshop on Content Generation and Coding for 3D-Television
Presented at:IEEE Workshop on Content Generation and Coding for 3D-Television 2006

BibTex PDF 



@inproceedings{scholz2006garmentmotion,
  title = {Multi-View Video Capture of Garment Motion},
  author = {Scholz, Volker and Magnor, Marcus},
  booktitle = {Proc. {IEEE} Workshop on Content Generation and Coding for 3D-Television},
  pages = {1--4},
  month = {Jun},
  year = {2006}
}

Authors