Sciweavers

302 search results - page 15 / 61
» Enforcing image consistency in multiple 3-D object modelling
Sort
View
SAC
2004
ACM
14 years 1 months ago
Concatenate feature extraction for robust 3D elliptic object localization
Developing an efficient object localization system for complicated industrial objects is an important, yet difficult robotic task. To tackle this problem, we have developed a syst...
Yuichi Motai, Akio Kosaka
ICIP
2005
IEEE
14 years 1 months ago
An active volumetric model for 3D reconstruction
—In this paper, we present an active volumetric model (AVM) for 3D reconstruction from multiple calibrated images of a scene. The AVM is a physically motivated 3D deformable mode...
Xin Liu, Hongxun Yao, Xilin Chen, Wen Gao
CVPR
2006
IEEE
14 years 2 months ago
Learning Joint Top-Down and Bottom-up Processes for 3D Visual Inference
We present an algorithm for jointly learning a consistent bidirectional generative-recognition model that combines top-down and bottom-up processing for monocular 3d human motion ...
Cristian Sminchisescu, Atul Kanaujia, Dimitris N. ...
IDMS
1997
Springer
153views Multimedia» more  IDMS 1997»
14 years 2 days ago
Embedding Data in 3D Models
The recent popularity of digital media such as CD-ROM and the Internet has prompted exploration of techniques for embedding data, either visibly or invisibly, into text, image, and...
Ryutarou Ohbuchi, Hiroshi Masuda, Masaki Aono
CVPR
2009
IEEE
14 years 2 months ago
Non-rigid 2D-3D pose estimation and 2D image segmentation
In this work, we present a non-rigid approach to jointly solve the tasks of 2D-3D pose estimation and 2D image segmentation. In general, most frameworks which couple both pose est...
Romeil Sandhu, Samuel Dambreville, Anthony J. Yezz...