Keenan Crane
Capturing and Animating Occluded Cloth
SIGGRAPH 2007 / ACM Transactions on Graphics
Ryan White Keenan Crane David Forsyth
University of California, Berkeley University of Illinois at Urbana-Champaign University of Illinois at Urbana-Champaign
We capture the shape of moving cloth using a custom set of color markers printed on the surface of the cloth. The output is a sequence of triangle meshes with static connectivity and with detail at the scale of individual markers in both smooth and folded regions. We compute markers' coordinates in space using marker correspondence across multiple synchronized video cameras. Correspondence is determined from color information in small neighborhoods and refined using a novel strain pruning process. Final correspondence does not require neighborhood information. We use a novel data driven hole-filling technique to fill occluded regions. Our results include several challenging examples: a wrinkled shirt sleeve, a dancing pair of pants, and a rag tossed onto a cup. Finally, we demonstrate that cloth capture is reusable by animating a pair of pants using human motion capture data.
PDF, 3.3MB
We thank Jai Vasanth and Anthony Lobay for early support of this project, Scott Kircher and Robert Sumner for providing mesh editing binaries, and Sony Computer Entertainment America for supplying human motion capture data. This work was supported in part by a Department of Homeland Security Fellowship and an ATI Graduate Research Fellowship.
@article{White:2007:CAO, author = {White, Ryan and Crane, Keenan and Forsyth, D. A.}, title = {Capturing and animating occluded cloth}, journal = {ACM Trans. Graph.}, volume = {26}, issue = {3}, month = {July}, year = {2007}, }
Computer Animation Festival
Cloth capture data.
(Various formats)