Viewpoint determination of image by interpolation over sparse samples

Authors:
Bodong Liang;Ronald Chung
Affiliations:
Department of Automation and Computer-Aided Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong, China;Department of Automation and Computer-Aided Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong, China
Venue:
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I
Year:
2006

Citing 11
Cited 0

Robust regression and outlier detection

Robust regression and outlier detection
Robust methods for estimating pose and a sensitivity analysis

CVGIP: Image Understanding
A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry

Artificial Intelligence - Special volume on computer vision
Linear N-Point Camera Pose Determination

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Trainable System for Object Detection

International Journal of Computer Vision - special issue on learning and vision at the center for biological and computational learning, Massachusetts Institute of Technology
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
Multiple view geometry in computer visiond

Multiple view geometry in computer visiond
Verbs and Adverbs: Multidimensional Motion Interpolation

IEEE Computer Graphics and Applications
Pose Estimation for Planar Structures

IEEE Computer Graphics and Applications
A New Efficient and Direct Solution for Pose Estimation Using Quadrangular Targets: Algorithm and Evaluation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Estimation of Relative Camera Positions for Uncalibrated Cameras

ECCV '92 Proceedings of the Second European Conference on Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

We address the problem of, given an image, determining the viewpoint from which the image was taken, and that is to be achieved without referencing to or estimating any explicit 3-D structure of the imaged scene. Used for reference are a small number of sample snapshots of the scene, each of which having the associated viewpoint supplied with it. By viewing image and its associated viewpoint as the input and output of a function, and the given snapshot-viewpoint pairs as samples of that function, we have a natural formulation of the problem as an interpolation or learning one. The interpolation formulation has at least two advantages: it allows imaging details like camera intrinsic parameters to be unknown, and the viewpoint specification to be not necessarily physical, i.e., the specification could consist of any set of values that adequately describe the viewpoint space and need not be measured in metric units. We describe an interpolation-based solution that guarantees that all given sample data are satisfied exactly with the least complexity in the interpolated function. Experimental results on benchmarking image dataset show that the solution is effective in arriving at good solution even with sparse input samples.