“Extracting Face Bump Maps From Video” by Paterson and Fitzgibbon
Conference:
Type:
Title:
- Extracting Face Bump Maps From Video
Presenter(s)/Author(s):
Abstract:
Accurate, realistic and efficient rendering of human faces is of great importance in graphics applications. For high-speed rendering, a low-fidelity 3D model may be effectively enhanced by the use of bump mapping techniques which superimpose high-resolution sur- face normal maps on low-resolution geometry. Traditionally, obtaining high-quality bump maps for human faces has required high- resolution 3D models, or complex studio-bound lighting rigs. In this sketch we describe progress towards the extraction of high- quality bump maps from a single video camera and a static light source.
References:
Debevec, P., Hawkins, T., Tchou, C., Duiker, H. P., Sarokin, W., and Sagar, M. 2000. Acquiring the reflectance field of a human face. In Proceedings of ACM SIGGRAPH, 145–156.
Ferrari, V., Tuytelaars, T., and Gool, L. V. 2003. Wide-baseline multiple-view correspondences. In Proc. CVPR, 718–725.
Paterson, J. A., and Fitzgibbon, A. W. 2002. Flexible bump map capture from video. In Eurographics Short Presentations, http://www.robots.ox.ac.uk/~jamie/paterson02.html.
Paterson, J. A., and Fitzgibbon, A. W. 2003. 3d head tracking using non-linear optimization. In Proc. BMVC., 609–618.
Rushmeier, H., Taubin, G., and Guéziec, A. 1997. Applying shape from lighting variation to bump map capture. In Proceedings, Eurographics Workshop on Rendering, 35–44.
Acknowledgements:
We would like to thank Sony Computer Entertainment Europe for their support of this project.
