by Graham, Paul, Fyffe, Graham, Tonwattanapong, Borom, Ghosh, Abhijeet and Debevec, Paul
Abstract:
Modeling realistic human characters is frequently done using 3D recordings of the shape and appearance of real people, often across a set of different facial expressions to build blendshape facial models. Believable characters that cross the "Uncanny Valley" require high-quality geometry, texture maps, reflectance properties, and surface detail at the level of skin pores and fine wrinkles. Unfortunately, there has not yet been a technique for recording such datasets that is near-instantaneous and low-cost. While some facial capture techniques are instantaneous and inexpensive [Beeler et al. 2010], these do not generally provide lighting-independent texture maps, specular reflectance information, or high-resolution surface normal detail for relighting. In contrast, techniques which use multiple photographs from spherical lighting setups [Ghosh et al. 2011] do capture such reflectance properties, at the expense of longer capture times and complicated custom equipment.
Reference:
Near-Instant Capture of High-Resolution Facial Geometry and Reflectance (Graham, Paul, Fyffe, Graham, Tonwattanapong, Borom, Ghosh, Abhijeet and Debevec, Paul), In Proceedings of ACM SIGGRAPH 2015 Talks, ACM Press, 2015.
Bibtex Entry:
@inproceedings{graham_near-instant_2015,
title = {Near-{Instant} {Capture} of {High}-{Resolution} {Facial} {Geometry} and {Reflectance}},
isbn = {978-1-4503-3636-9},
url = {http://ict.usc.edu/pubs/Near-Instant%20Capture%20of%20High-Resolution%20Facial%20Geometry%20and%20Reflectance.pdf},
doi = {10.1145/2775280.2792561},
abstract = {Modeling realistic human characters is frequently done using 3D recordings of the shape and appearance of real people, often across a set of different facial expressions to build blendshape facial models. Believable characters that cross the "Uncanny Valley" require high-quality geometry, texture maps, reflectance properties, and surface detail at the level of skin pores and fine wrinkles. Unfortunately, there has not yet been a technique for recording such datasets that is near-instantaneous and low-cost. While some facial capture techniques are instantaneous and inexpensive [Beeler et al. 2010], these do not generally provide lighting-independent texture maps, specular reflectance information, or high-resolution surface normal detail for relighting. In contrast, techniques which use multiple photographs from spherical lighting setups [Ghosh et al. 2011] do capture such reflectance properties, at the expense of longer capture times and complicated custom equipment.},
booktitle = {Proceedings of {ACM} {SIGGRAPH} 2015 {Talks}},
publisher = {ACM Press},
author = {Graham, Paul and Fyffe, Graham and Tonwattanapong, Borom and Ghosh, Abhijeet and Debevec, Paul},
month = aug,
year = {2015},
keywords = {Graphics, UARC},
pages = {1--1}
}