Event Location: NSH 1507
Bio: Yuandong Tian is currently a second-year Ph.D candidate in Robotics, Carnegie Mellon University. His research interest is computer vision and machine learning. He is now working on distortion estimation of images. He received his Bachelor and Master degree in Computer Science from Shanghai Jiao Tong University in 2005 and 2008 respectively.

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 $epsilon$-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.