Sciweavers

88 search results - page 16 / 18
» Space and camera path reconstruction for omni-directional vi...
Sort
View
CVPR
2008
IEEE
14 years 7 months ago
High resolution motion layer decomposition using dual-space graph cuts
We introduce a novel energy minimization method to decompose a video into a set of super-resolved moving layers. The proposed energy corresponds to the cost of coding the sequence...
Thomas Schoenemann, Daniel Cremers
ICCV
2005
IEEE
14 years 7 months ago
Multi-Modal Tensor Face for Simultaneous Super-Resolution and Recognition
Face images of non-frontal views under poor illumination with low resolution reduce dramatically face recognition accuracy. This is evident most compellingly by the very low recog...
Kui Jia, Shaogang Gong
ICASSP
2011
IEEE
12 years 9 months ago
Compression using self-similarity-based temporal super-resolution for full-exposure-time video
In order to allow sufficient amount of light into the image sensor, videos captured in poor lighting conditions typically have low frame rate and frame exposure time equals to in...
Mihoko Shimano, Gene Cheung, Imari Sato
CVPR
2009
IEEE
1378views Computer Vision» more  CVPR 2009»
15 years 4 hour ago
A Novel Feature Descriptor Invariant to Complex Brightness Changes
We describe a novel and robust feature descriptor called ordinal spatial intensity distribution (OSID) which is invariant to any monotonically increasing brightness changes. Many t...
Feng Tang, Suk Hwan Lim, Nelson L. Chang, Hai Tao
CVPR
2008
IEEE
14 years 7 months ago
Quasi-perspective projection with applications to 3D factorization from uncalibrated image sequences
The paper addresses the problem of factorization-based 3D reconstruction from uncalibrated image sequences. We propose a quasi-perspective projection model and apply the model to ...
Guanghui Wang, Q. M. Jonathan Wu, Guoqiang Sun