A Globally Optimal Data-Driven Approach for Image Distortion Estimation

June 2010

A Globally Optimal Data-Driven Approach for Image Distortion Estimation

Authors:

Y. Tian and S. G. Narasimhan
Conference Paper
Proceedings of (CVPR) Computer Vision and Pattern Recognition

Abstract:

Image alignment in the presence of non-rigid distortions is a challenging task. Typically, this involves estimating the parameters of a dense deformation field that warps a distorted image back to its undistorted template. Generative approaches based on parameter optimization such as Lucas-Kanade can get trapped within local minima. On the other hand, discriminative approaches like Nearest-Neighbor require a large number of training samples that grows exponentially with the desired accuracy. In this work, we develop a novel data-driven iterative algorithm that combines the best of both generative and discriminative approaches. For this, we introduce the notion of a “pull-back” operation that enables us to predict the parameters of the test image using training samples that are not in its neighborhood (not ϵ-close) in parameter space. We prove that our algorithm converges to the global optimum using a significantly lower number of training samples that grows only logarithmically with the desired accuracy. We analyze the behavior of our algorithm extensively using synthetic data and demonstrate successful results on experiments with complex deformations due to water and clothing.
@conference{Tian-2010-120331,
author = {Y. Tian And S. G. Narasimhan},
title = {A Globally Optimal Data-Driven Approach for Image Distortion Estimation},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {2010},
month = {June},
pages = {1277 - 1284},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.