Sciweavers

314 search results - page 62 / 63
» Segmentation Using Multiscale Cues
Sort
View
NIPS
2008
13 years 7 months ago
Grouping Contours Via a Related Image
Contours have been established in the biological and computer vision literature as a compact yet descriptive representation of object shape. While individual contours provide stru...
Praveen Srinivasan, Liming Wang, Jianbo Shi
ICCV
2009
IEEE
13 years 4 months ago
Estimating human shape and pose from a single image
We describe a solution to the challenging problem of estimating human body shape from a single photograph or painting. Our approach computes shape and pose parameters of a 3D huma...
Peng Guan, Alexander Weiss, Alexandru O. Balan, Mi...
ICCV
2009
IEEE
14 years 11 months ago
Piecewise Planar Stereo for Image-based Rendering
We present a novel multi-view stereo method designed for image-based rendering that generates piecewise planar depth maps from an unordered collection of photographs. First a di...
Sudipta N. Sinha, Drew Steedly and Richard Szelisk...
CVPR
2009
IEEE
1453views Computer Vision» more  CVPR 2009»
14 years 10 months ago
Learning Photometric Invariance From Diversified Color Model Ensembles
Color is a powerful visual cue for many computer vision applications such as image segmentation and object recognition. However, most of the existing color models depend on the i...
Jose M. Alvarez, Theo Gevers, Antonio M. Lopez
MM
2004
ACM
212views Multimedia» more  MM 2004»
13 years 11 months ago
Nonparametric motion model
Motion information is a powerful cue for visual perception. In the context of video indexing and retrieval, motion content serves as a useful source for compact video representati...
Ling-Yu Duan, Min Xu, Qi Tian, Changsheng Xu