Sciweavers

886 search results - page 157 / 178
» Computing Visual Attention from Scene Depth
Sort
View
ICMCS
2007
IEEE
101views Multimedia» more  ICMCS 2007»
15 years 4 months ago
View-Dependent Visibility Estimation for Tree Models
— A view-dependent visibility estimation technique for tree models is proposed in this work. While most previous work focused on visibility estimation of large objects in archite...
Jessy Lee, Jingliang Peng, C. C. Jay Kuo
3DPVT
2004
IEEE
136views Visualization» more  3DPVT 2004»
15 years 1 months ago
Efficient Model Creation of Large Structures based on Range Segmentation
This paper describes an efficient 3D modeling method from 3D range data-sets that is utilizing range data segmentation. Our algorithm starts with a set of unregistered 3D range sc...
Ioannis Stamos, Marius Leordeanu
SSIAI
2000
IEEE
15 years 2 months ago
A New Bayesian Relaxation Framework for the Estimation and Segmentation of Multiple Motions
In this paper we propose a new probabilistic relaxation framework to perform robust multiple motion estimation and segmentation from a sequence of images. Our approach uses displa...
Alexander Strehl, Jake K. Aggarwal
FGR
2004
IEEE
126views Biometrics» more  FGR 2004»
15 years 1 months ago
Trainable Videorealistic Speech Animation
We describe how to create with machine learning techniques a generative, videorealistic, speech animation module. A human subject is first recorded using a videocamera as he/she u...
Tony Ezzat, Gadi Geiger, Tomaso Poggio
PG
2007
IEEE
15 years 4 months ago
Multilinear Motion Synthesis with Level-of-Detail Controls
Interactive animation systems often use a level-of-detail (LOD) control to reduce the computational cost by eliminating unperceivable details of the scene. Most methods employ a m...
Tomohiko Mukai, Shigeru Kuriyama