Robust Non-parametric Data Fitting for Correspondence Modeling

Wen-Yan Lin, Ming-Ming Cheng, Shuai Zheng, Jiangbo Lu, Nigel Crook; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2013, pp. 2376-2383

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Lin_2013_ICCV,
author = {Lin, Wen-Yan and Cheng, Ming-Ming and Zheng, Shuai and Lu, Jiangbo and Crook, Nigel},
title = {Robust Non-parametric Data Fitting for Correspondence Modeling},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2013}
}