Title
Temporal upsampling of performance geometry using photometric alignment
Abstract
We present a novel technique for acquiring detailed facial geometry of a dynamic performance using extended spherical gradient illumination. Key to our method is a new algorithm for jointly aligning two photographs, under a gradient illumination condition and its complement, to a full-on tracking frame, providing dense temporal correspondences under changing lighting conditions. We employ a two-step algorithm to reconstruct detailed geometry for every captured frame. In the first step, we coalesce information from the gradient illumination frames to the full-on tracking frame, and form a temporally aligned photometric normal map, which is subsequently combined with dense stereo correspondences yielding a detailed geometry. In a second step, we propagate the detailed geometry back to every captured instance guided by the previously computed dense correspondences. We demonstrate reconstructed dynamic facial geometry, captured using moderate to video rates of acquisition, for every captured frame.
Year
DOI
Venue
2010
10.1145/1731047.1731055
ACM Trans. Graph.
Keywords
Field
DocType
gradient illumination condition,photorealism,photometric alignment,gradient illumination frame,motion estimation,detailed geometry,3d face scanning,dynamic facial geometry,extended spherical gradient illumination,optical flow,performance geometry,dense stereo,dense temporal correspondence,full-on tracking frame,temporal upsampling,capture,detailed facial geometry,dense correspondence
Computer vision,Facial geometry,Photometry (optics),Artificial intelligence,Motion estimation,Upsampling,Optical flow,Mathematics
Journal
Volume
Issue
ISSN
29
2
0730-0301
Citations 
PageRank 
References 
31
1.54
17
Authors
6
Name
Order
Citations
PageRank
Cyrus A. Wilson11239.32
Abhijeet Ghosh277258.87
Pieter Peers3110955.34
Jen-Yuan Chiang4573.98
Jay Busch528323.06
Paul Debevec64955449.10