Sciweavers

6005 search results - page 910 / 1201
» Graph-Theoretical Methods in Computer Vision
Sort
View
CVPR
2009
IEEE
17 years 1 months ago
Capturing 3D Stretchable Surfaces from Single Images in Closed Form
We present a closed-form solution to the problem of recovering the 3D shape of a non-rigid potentially stretchable surface from 3D-to-2D correspondences. In other words, we can ...
Francesc Moreno-Noguer (Institut de Robotica i Inf...
CVPR
2009
IEEE
1131views Computer Vision» more  CVPR 2009»
17 years 1 months ago
Continuous Depth Estimation for Multi-view Stereo
Depth-map merging approaches have become more and more popular in multi-view stereo (MVS) because of their flexibility and superior performance. The quality of depth map used fo...
Yebin Liu (Tsinghua University), Xun Cao (Tsinghu...
CVPR
2009
IEEE
17 years 1 months ago
Nonrigid Registration Combining Global and Local Statistics
In this paper we exploit normalized mutual information for the nonrigid registration of multimodal images. Rather than assuming that image statistics are spatially stationary, a...
Zhao Yi (UCLA), Stefano Soatto (UCLA)
CVPR
2009
IEEE
17 years 1 months ago
Discriminative Structure Learning of Hierarchical Representations for Object Detection
A variety of flexible models have been proposed to detect objects in challenging real world scenes. Motivated by some of the most successful techniques, we propose a hierarchica...
Paul Schnitzspan (TU Darmstadt), Mario Fritz (Univ...
CVPR
2009
IEEE
17 years 1 months ago
What's It Going to Cost You?: Predicting Effort vs. Informativeness for Multi-Label Image Annotations
Active learning strategies can be useful when manual labeling effort is scarce, as they select the most informative examples to be annotated first. However, for visual category ...
Sudheendra Vijayanarasimhan (University of Texas a...