Sciweavers

1351 search results - page 36 / 271
» Learning 3D Appearance Models from Video
Sort
View
ICCV
2007
IEEE
14 years 3 months ago
Action Recognition from Arbitrary Views using 3D Exemplars
In this paper, we address the problem of learning compact, view-independent, realistic 3D models of human actions recorded with multiple cameras, for the purpose of recognizing th...
Daniel Weinland, Edmond Boyer, Rémi Ronfard
AAAI
2008
13 years 11 months ago
Make3D: Depth Perception from a Single Still Image
Humans have an amazing ability to perceive depth from a single still image; however, it remains a challenging problem for current computer vision systems. In this paper, we will p...
Ashutosh Saxena, Min Sun, Andrew Y. Ng
NECO
2007
152views more  NECO 2007»
13 years 8 months ago
3D Periodic Human Motion Reconstruction from 2D Motion Sequences
In this report, we present and evaluate a method of reconstructing three-dimensional (3D) periodic human motion from two-dimensional (2D) motion sequences. Based on a Fourier deco...
Zonghua Zhang, Nikolaus F. Troje
CVPR
2008
IEEE
14 years 10 months ago
Simultaneous super-resolution and 3D video using graph-cuts
This paper presents a new method to increase the quality of 3D video, a new media developed to represent 3D objects in motion. This representation is obtained from multi-view reco...
Tony Tung, Shohei Nobuhara, Takashi Matsuyama
CVPR
2007
IEEE
14 years 10 months ago
Bridging the Gap between Detection and Tracking for 3D Monocular Video-Based Motion Capture
We combine detection and tracking techniques to achieve robust 3?D motion recovery of people seen from arbitrary viewpoints by a single and potentially moving camera. We rely on d...
Andrea Fossati, Miodrag Dimitrijevic, Vincent Lepe...