Sciweavers

150 search results - page 26 / 30
» The Minimum Description Length Principle in Coding and Model...
Sort
View
FGR
2008
IEEE
301views Biometrics» more  FGR 2008»
14 years 2 months ago
3D facial geometry recovery via group-wise optical flow
We describe an algorithm for automatically finding correspondences from face video sequences. This method is useful to many applications such as face tracking, face modeling and ...
Hui Fang, Nicholas Costen, David Cristinacce, John...
CORR
2007
Springer
113views Education» more  CORR 2007»
13 years 7 months ago
Communication under Strong Asynchronism
We consider asynchronous communication over point-to-point discrete memoryless channels without feedback. The transmitter starts sending one block codeword at an instant that is u...
Aslan Tchamkerten, Venkat Chandar, Gregory W. Worn...
ECCV
2006
Springer
14 years 9 months ago
Resolution-Enhanced Photometric Stereo
Abstract. Conventional photometric stereo has a fundamental limitation that the scale of recovered geometry is limited to the resolution of the input images. However, surfaces that...
Ping Tan, Stephen Lin, Long Quan
ICCV
2003
IEEE
14 years 28 days ago
Unsupervised Non-parametric Region Segmentation Using Level Sets
We present a novel non-parametric unsupervised segmentation algorithm based on Region Competition [21]; but implemented within a Level Sets framework [11]. The key novelty of the ...
Timor Kadir, Michael Brady
PAMI
2008
157views more  PAMI 2008»
13 years 7 months ago
Subpixel Photometric Stereo
Conventional photometric stereo recovers one normal direction per pixel of the input image. This fundamentally limits the scale of recovered geometry to the resolution of the input...
Ping Tan, Stephen Lin, Long Quan