Sciweavers

6005 search results - page 425 / 1201
» Graph-Theoretical Methods in Computer Vision
Sort
View
163
Voted
ECCV
2008
Springer
16 years 9 months ago
Shape Matching by Segmentation Averaging
We use segmentations to match images by shape. To address the unreliability of segmentations, we give a closed form approximation to an average over all segmentations. Our techniqu...
Hongzhi Wang, John Oliensis
ECCV
2004
Springer
16 years 9 months ago
Multiple View Feature Descriptors from Image Sequences via Kernel Principal Component Analysis
Abstract. We present a method for learning feature descriptors using multiple images, motivated by the problems of mobile robot navigation and localization. The technique uses the ...
Jason Meltzer, Ming-Hsuan Yang, Rakesh Gupta, Stef...
214
Voted
ECCV
2006
Springer
16 years 9 months ago
SURF: Speeded Up Robust Features
In this paper, we present a novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features). It approximates or even outperform...
Herbert Bay, Tinne Tuytelaars, Luc J. Van Gool
ECCV
2006
Springer
16 years 9 months ago
Robust and Efficient Photo-Consistency Estimation for Volumetric 3D Reconstruction
Estimating photo-consistency is one of the most important ingredients for any 3D stereo reconstruction technique that is based on a volumetric scene representation. This paper pres...
Alexander Hornung, Leif Kobbelt
197
Voted
ICPR
2008
IEEE
16 years 8 months ago
Usage of needle maps and shadows to overcome depth edges in depth map reconstruction
Photometric stereo is a method of recovering surface normals (needle map) from images. The surface integral of surface normals is used to reconstruct a depth map; however, the dep...
Koh Kakusho, Koki Hamada, Masaaki Iiyama, Michihik...