Sciweavers

ICCV
2009
IEEE
15 years 4 months ago
Is Dual Linear Self-Calibration Artificially Ambiguous?
This purely theoretical work investigates the problem of artificial singularities in camera self-calibration. Selfcalibration allows one to upgrade a projective reconstruction t...
Pierre Gurdjos, Adrien Bartoli, Peter Sturm
ICCV
2009
IEEE
1735views Computer Vision» more  ICCV 2009»
15 years 4 months ago
Coded Aperture Pairs for Depth From Defocus
The classical approach to depth from defocus uses two images taken with circular apertures of different sizes. We show in this paper that the use of a circular aperture severely...
Changyin Zhou, Stephen Lin, Shree Nayar
ICCV
2009
IEEE
15 years 4 months ago
Decomposing a Scene into Geometric and Semantically Consistent Regions
High-level, or holistic, scene understanding involves reasoning about objects, regions, and the 3D relationships between them. This requires a representation above the level of ...
Stephen Gould, Richard Fulton, Daphne Koller
ICCV
2009
IEEE
15 years 4 months ago
Compact Signatures for High-Speed Interest Point Description and Matching
Prominent feature point descriptors such as SIFT and SURF allow reliable real-time matching but at a compu- tational cost that limits the number of points that can be handled on...
Michael Calonder, Vincent Lepetit, Pascal Fua, Kur...
ICCV
2009
IEEE
1069views Computer Vision» more  ICCV 2009»
15 years 4 months ago
An efficient algorithm for Co-segmentation
This paper is focused on the Co-segmentation problem [1] – where the objective is to segment a similar object from a pair of images. The background in the two images may be ar...
Dorit S. Hochbaum, Vikas Singh
ICCV
2009
IEEE
15 years 4 months ago
A Shape-Based Object Class Model for Knowledge Transfer
Object class models trained on hundreds or thousands of images have shown to enable robust detection. Transferring knowledge from such models to new object classes trained from ...
Michael Stark, Michael Goesele, Bernt Schiele
ICCV
2009
IEEE
1556views Computer Vision» more  ICCV 2009»
15 years 4 months ago
Kernel Methods for Weakly Supervised Mean Shift Clustering
Mean shift clustering is a powerful unsupervised data analysis technique which does not require prior knowledge of the number of clusters, and does not constrain the shape of th...
Oncel Tuzel, Fatih Porikli, Peter Meer
ICCV
2009
IEEE
15 years 4 months ago
TagProp: Discriminative Metric Learning in Nearest Neighbor Models for Image Auto-Annotation
Image auto-annotation is an important open problem in computer vision. For this task we propose TagProp, a discriminatively trained nearest neighbor model. Tags of test images a...
Matthieu Guillaumin, Thomas Mensink, Jakob Verbeek...
ICCV
2009
IEEE
15 years 4 months ago
Curvature Regularity for Region-based Image Segmentation and Inpainting: A Linear Programming Relaxation
We consider a class of region-based energies for image segmentation and inpainting which combine region integrals with curvature regularity of the region boundary. To minimize s...
Thomas Schoenemann, Fredrik Kahl, Daniel Cremers
ICCV
2009
IEEE
1655views Computer Vision» more  ICCV 2009»
15 years 4 months ago
Shift-Map Image Editing
Geometric rearrangement of images includes operations such as image retargeting, inpainting, or object rearrangement. Each such operation can be characterized by a shiftmap: the...
Yael Pritch, Eitam Kav-Venaki, Shmuel Peleg