DMCA
Spacetime faces: High resolution capture for modeling and animation (2004)
| Venue: | IN ACM TRANSACTIONS ON GRAPHICS (PROC. OF ACM SIGGRAPH) |
| Citations: | 193 - 7 self |
BibTeX
@ARTICLE{Zhang04spacetimefaces:,
author = {Li Zhang and Noah Snavely and Brian Curless and Steven M. Seitz},
title = { Spacetime faces: High resolution capture for modeling and animation},
journal = {IN ACM TRANSACTIONS ON GRAPHICS (PROC. OF ACM SIGGRAPH) },
year = {2004},
pages = {548--558}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We present an end-to-end system that goes from video sequences to high resolution, editable, dynamically controllable face models. The capture system employs synchronized video cameras and structured light projectors to record videos of a moving face from multiple viewpoints. A novel spacetime stereo algorithm is introduced to compute depth maps accurately and overcome over-fitting deficiencies in prior work. A new template fitting and tracking procedure fills in missing data and yields point correspondence across the entire sequence without using markers. We demonstrate a datadriven, interactive method for inverse kinematics that draws on the large set of fitted templates and allows for posing new expressions by dragging surface points directly. Finally, we describe new tools that model the dynamics in the input sequence to enable new animations, created via key-framing or texture-synthesis techniques.
Keyphrases
high resolution capture video sequence fitted template over-fitting deficiency new animation light projector inverse kinematics controllable face model entire sequence tracking procedure fill yield point correspondence depth map capture system new tool end-to-end system surface point large set high resolution new template fitting texture-synthesis technique prior work synchronized video camera new expression novel spacetime stereo algorithm multiple viewpoint interactive method input sequence
