Sciweavers

895 search results - page 154 / 179
» Estimating Human Pose from Occluded Images
Sort
View
112
Voted
ECCV
2006
Springer
14 years 11 months ago
Robust Face Alignment Based on Hierarchical Classifier Network
Abstract. Robust face alignment is crucial for many face processing applications. As face detection only gives a rough estimation of face region, one important problem is how to al...
Li Zhang, Haizhou Ai, Shihong Lao
3DPVT
2006
IEEE
295views Visualization» more  3DPVT 2006»
14 years 11 months ago
Efficient Sparse 3D Reconstruction by Space Sweeping
This paper introduces a feature based method for the fast generation of sparse 3D point clouds from multiple images with known pose. We extract sub-pixel edge elements (2D positio...
Joachim Bauer, Christopher Zach, Horst Bischof
ICIP
2004
IEEE
15 years 11 months ago
Complete 3-d models from video: a global approach
We address the automatic recovery of complete 3-D object models from video streams. Usually, complete 3-D models are built by fusing several depth maps, each computed from a small...
Bruno B. Gonçalves, Pedro M. Q. Aguiar
81
Voted
MM
2009
ACM
196views Multimedia» more  MM 2009»
15 years 4 months ago
Mirror world navigation for mobile users based on augmented reality
Finding a destination in unfamiliar environments of complex office building or shopping mall has been always bothering us in daily life. Fine-scale directional guidance, a combina...
Patricia P. Wang, Tao Wang, Dayong Ding, Yimin Zha...
ISBI
2007
IEEE
15 years 3 months ago
Splitting Tracking through Crossing Fibers: Multidirectional Q-Ball Tracking
We present a new tracking algorithm based on the full multidirectional information of the diffusion orientation distribution function (ODF) estimated from Q-Ball Imaging (QBI). Fr...
Rachid Deriche, Maxime Descoteaux