Robust non-parametric data fitting for correspondence modeling

Robust non-parametric data fitting for correspondence modeling

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 consiste...

Full description

Saved in:
Bibliographic Details
Main Authors: LIN, Wen-yan, CHENG, Ming-Ming, ZHENG, Shuai, LU, Jiangbo, CROOK, Nigel
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2013
Subjects:
curve fitting
matching
non-parametric
spline; warping
Graphics and Human Computer Interfaces
Online Access:https://ink.library.smu.edu.sg/sis_research/4809
https://ink.library.smu.edu.sg/context/sis_research/article/5812/viewcontent/DataFittingICCV13.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
Description
Summary: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.

Similar Items