Globally Optimal Estimation of Nonrigid Image Distortion

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 nearestneighbor require a large number of training samples that grows exponentially with respect to the dimension of the parameter space, and polynomially with the desired accuracy 1/ . 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 -close) in the parameter space. We prove that our algorithm converges to the global optimum usi...

• Type: Journal
• Year: 2012
• Where: IJCV
• Authors: Yuandong Tian, Srinivasa G. Narasimhan
• Keywords: Computer Networks, IJCV 2012, Image Alignment, Parameter Optimization, Parameter Space