Sciweavers

129 search results - page 5 / 26
» Computing the Physical Parameters of Rigid-Body Motion from ...
Sort
View
PG
2003
IEEE
14 years 1 months ago
Enhancing Silhouette-Based Human Motion Capture with 3D Motion Fields
High-quality non-intrusive human motion capture is necessary for acquistion of model-based free-viewpoint video of human actors. Silhouette-based approaches have demonstrated that...
Christian Theobalt, Joel Carranza, Marcus A. Magno...
ICCV
2005
IEEE
14 years 10 months ago
Shape Recovery of 3D Data Obtained from a Moving Range Sensor by Using Image Sequences
For a large object, scanning from the air is one of the most efficient methods of obtaining 3D data. But in the case of large cultural heritage objects, there are some difficultie...
Atsuhiko Banno, Katsushi Ikeuchi
ICCV
2003
IEEE
14 years 10 months ago
Shape and Motion under Varying Illumination: Unifying Structure from Motion, Photometric Stereo, and Multi-view Stereo
This paper presents an algorithm for computing optical flow, shape, motion, lighting, and albedo from an image sequence of a rigidly-moving Lambertian object under distant illumin...
Li Zhang, Brian Curless, Aaron Hertzmann, Steven M...
CVPR
2012
IEEE
11 years 10 months ago
Discovering discriminative action parts from mid-level video representations
We describe a mid-level approach for action recognition. From an input video, we extract salient spatio-temporal structures by forming clusters of trajectories that serve as candi...
Michalis Raptis, Iasonas Kokkinos, Stefano Soatto
ISCIS
2003
Springer
14 years 1 months ago
Model-Based Human Motion Capture from Monocular Video Sequences
Generating motion and capturing motion of an articulated body for computer animation is an expensive and time-consuming task. Conventionally, animators manually generate intermedia...
Jihun Park, Sangho Park, Jake K. Aggarwal