Sciweavers

7326 search results - page 1131 / 1466
» Methods for modalities 3
Sort
View
ECCV
2008
Springer
16 years 8 months ago
Integration of Multiview Stereo and Silhouettes Via Convex Functionals on Convex Domains
We propose a convex framework for silhouette and stereo fusion in 3D reconstruction from multiple images. The key idea is to show that the reconstruction problem can be cast as one...
Kalin Kolev, Daniel Cremers
ECCV
2006
Springer
16 years 8 months ago
Scene Classification Via pLSA
Given a set of images of scenes containing multiple object categories (e.g. grass, roads, buildings) our objective is to discover these objects in each image in an unsupervised man...
Anna Bosch, Andrew Zisserman, Xavier Muñoz
ECCV
2006
Springer
16 years 8 months ago
Shape-from-Silhouette with Two Mirrors and an Uncalibrated Camera
Two planar mirrors are positioned to show five views of an object, and snapshots are captured from different viewpoints. We present closed form solutions for calculating the focal ...
Keith Forbes, Fred Nicolls, Gerhard de Jager, Anth...
ECCV
2006
Springer
16 years 8 months ago
Multivariate Relevance Vector Machines for Tracking
This paper presents a learning based approach to tracking articulated human body motion from a single camera. In order to address the problem of pose ambiguity, a one-to-many mappi...
Arasanathan Thayananthan, Ramanan Navaratnam, Bj&o...
ECCV
2002
Springer
16 years 8 months ago
Nonlinear Shape Statistics in Mumford-Shah Based Segmentation
We present a variational integration of nonlinear shape statistics into a Mumford?Shah based segmentation process. The nonlinear statistics are derived from a set of training silho...
Christoph Schnörr, Daniel Cremers, Timo Kohlb...
« Prev « First page 1131 / 1466 Last » Next »