Sciweavers

895 search results - page 154 / 179
» Estimating Human Pose from Occluded Images
Sort
View
ECCV
2006
Springer
15 years 1 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»
15 years 1 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
16 years 1 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
MM
2009
ACM
196views Multimedia» more  MM 2009»
15 years 6 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 6 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