Sciweavers

366 search results - page 55 / 74
» FeatureBoost: A Meta-Learning Algorithm that Improves Model ...
Sort
View
CVPR
2009
IEEE
13 years 11 months ago
High-quality curvelet-based motion deblurring from an image pair
One promising approach to remove motion deblurring is to recover one clear image using an image pair. Existing dual-image methods require an accurate image alignment between the i...
Jian-Feng Cai, Hui Ji, Chaoqiang Liu, Zuowei Shen
ICMCS
2009
IEEE
218views Multimedia» more  ICMCS 2009»
13 years 5 months ago
Multi-view reconstruction under varying illumination conditions
This paper addresses the problem of complete and detailed 3D model reconstruction of objects filmed by multiple cameras under varying illumination. Firstly, initial normal maps ar...
Chenglei Wu, Yebin Liu, Xiangyang Ji, Qionghai Dai
ICCV
2005
IEEE
14 years 9 months ago
Geometric Context from a Single Image
Many computer vision algorithms limit their performance by ignoring the underlying 3D geometric structure in the image. We show that we can estimate the coarse geometric propertie...
Derek Hoiem, Alexei A. Efros, Martial Hebert
ICIP
2009
IEEE
14 years 8 months ago
Learning Large Margin Likelihoods For Realtime Head Pose Tracking
We consider the problem of head tracking and pose estimation in realtime from low resolution images. Tracking and pose recognition are treated as two coupled problems in a probabi...
EMMCVPR
2003
Springer
14 years 25 days ago
Surface Recovery from 3D Point Data Using a Combined Parametric and Geometric Flow Approach
This paper presents a novel method for surface recovery from discrete 3D point data sets. In order to produce improved reconstruction results, the algorithm presented in this paper...
Peter Savadjiev, Frank P. Ferrie, Kaleem Siddiqi