Sciweavers

1546 search results - page 183 / 310
» Computing Pose Sequences Directly from Videos
Sort
View
ICCV
2005
IEEE
14 years 10 months ago
Multi-Scale Gesture Recognition from Time-Varying Contours
A novel method is introduced to recognize and estimate the scale of time-varying human gestures. It exploits the changes in contours along spatio-temporal directions. Each contour...
Hong Li, Michael A. Greenspan
SMILE
1998
Springer
14 years 1 months ago
From Ordinal to Euclidean Reconstruction with Partial Scene Calibration
Abstract. Since uncalibrated images permit only projective reconstruction, metric information requires either camera or scene calibration. We propose a stratified approach to proje...
Daphna Weinshall, P. Anandan, Michal Irani
ICIP
2009
IEEE
13 years 6 months ago
Optical flow and depth from motion for omnidirectional images using a TV-L1 variational framework on graphs
This paper deals with the problem of efficiently computing the optical flow of image sequences acquired by omnidirectional (nearly full field of view) cameras. We formulate the pr...
Luigi Bagnato, Pascal Frossard, Pierre Vandergheyn...
SI3D
1992
ACM
14 years 29 days ago
Lights from Highlights and Shadows
Designing the illumination of a scene is a di cult task because one needs to render the whole scene in order to look at the result. Obtaining the correct lighting e ects may requi...
Pierre Poulin, Alain Fournier
CVPR
2005
IEEE
14 years 11 months ago
Reflections on the Generalized Bas-Relief Ambiguity
Prior work has argued that when a Lambertian surface in fixed pose is observed in multiple images under varying distant illumination, there is an equivalence class of surfaces giv...
Manmohan Krishna Chandraker, Fredrik Kahl, David J...