Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

1-2013

Abstract

We propose a generic method for obtaining nonparametric image warps from noisy point correspondences. Our formulation integrates a huber function into a motion coherence framework. This makes our fitting function especially robust to piecewise correspondence noise (where an image section is consistently mismatched). By utilizing over parameterized curves, we can generate realistic nonparametric image warps from very noisy correspondence. We also demonstrate how our algorithm can be used to help stitch images taken from a panning camera by warping the images onto a virtual push-broom camera imaging plane.

Keywords

curve fitting, matching, non-parametric, spline; warping

Discipline

Graphics and Human Computer Interfaces

Research Areas

Data Science and Engineering

Publication

Proceedings of the 14th IEEE International Conference on Computer Vision, ICCV 2013, Sydney, December 1-8

First Page

2376

Last Page

2383

ISBN

9781479928392

Identifier

10.1109/ICCV.2013.295

Publisher

IEEE

City or Country

Sydney, Australia

Additional URL

https://doi.org/10.1109/ICCV.2013.295

Share

COinS