Viewpoint induced deformation statistics and the design of viewpoint invariant features: singularities and occlusions

Authors:
Andrea Vedaldi;Stefano Soatto
Affiliations:
University of California at Los Angeles, Los Angeles, CA;University of California at Los Angeles, Los Angeles, CA
Venue:
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Year:
2006

Citing 23
Cited 0

Active shape models—their training and application

Computer Vision and Image Understanding
Feature Detection with Automatic Scale Selection

International Journal of Computer Vision
The Geometry and Matching of Curves in Multiple Views

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
An Affine Invariant Interest Point Detector

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
On Pencils of Tangent Planes and the Recognition of Smooth 3D Shapes from Silhouettes

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Unsupervised Learning of Models for Recognition

ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part I
Textons, Contours and Regions: Cue Integration in Image Segmentation

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Feature Selection for Unsupervised and Supervised Inference: the Emergence of Sparsity in a Weighted-based Approach

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Towards a Mathematical Theory of Primal Sketch and Sketchability

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Video Google: A Text Retrieval Approach to Object Matching in Videos

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Incorporating Background Invariance into Feature-Based Object Recognition

WACV-MOTION '05 Proceedings of the Seventh IEEE Workshops on Application of Computer Vision (WACV/MOTION'05) - Volume 1 - Volume 01
A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Efficient Image Matching with Distributions of Local Invariant Features

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
On the Spatial Statistics of Optical Flow

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Features for Recognition: Viewpoint Invariance for Non-Planar Scenes

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
A novel performance evaluation method of local detectors on non-planar scenes

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops - Volume 03
A Comparison of Affine Region Detectors

International Journal of Computer Vision
Rapid object recognition from discriminative regions of interest

AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Learning object detection from a small number of examples: the importance of good features

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Integrating multiple model views for object recognition

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Feature selection by maximum marginal diversity: optimality and implications for visual recognition

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

We study the set of domain deformations induced on images of three-dimensional scenes by changes of the vantage point. We parametrize such deformations and derive empirical statistics on the parameters, that show a kurtotic behavior similar to that of natural image and range statistics. Such a behavior would suggest that most deformations are locally smooth, and therefore could be captured by simple parametric maps, such as affine ones. However, we show that deformations induced by singularities and occluding boundaries, although rare, are highly salient, thus warranting the development of dedicated descriptors. We therefore illustrate the development of viewpoint invariant descriptors for singularities, as well as for occluding boundaries. We test their performance on scenes where the current state of the art based on affine-invariant region descriptors fail to establish correspondence, highlighting the features and shortcomings of our approach.