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.
Viewpoint Determination of Image by Interpolation over Sparse Samples
Computer Vision – ACCV 2006 ; 4 ; 399-408
Lecture Notes in Computer Science ; 3851 , 4
2006-01-01
10 pages
Article/Chapter (Book)
Electronic Resource
English
Viewpoint Determination of Image by Interpolation over Sparse Samples
British Library Conference Proceedings | 2006
|Viewpoint determination of image by interpolation over sparse samples
British Library Online Contents | 2008
|Image interpolation correspondence with viewpoint [3545-78]
British Library Conference Proceedings | 1998
|European Patent Office | 2021
|