A Globally Optimal Data-Driven Approach for Image Distortion Estimation
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
Cite
Text
Tian and Narasimhan. "A Globally Optimal Data-Driven Approach for Image Distortion Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5539822Markdown
[Tian and Narasimhan. "A Globally Optimal Data-Driven Approach for Image Distortion Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/tian2010cvpr-globally/) doi:10.1109/CVPR.2010.5539822BibTeX
@inproceedings{tian2010cvpr-globally,
title = {{A Globally Optimal Data-Driven Approach for Image Distortion Estimation}},
author = {Tian, Yuandong and Narasimhan, Srinivasa G.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2010},
pages = {1277-1284},
doi = {10.1109/CVPR.2010.5539822},
url = {https://mlanthology.org/cvpr/2010/tian2010cvpr-globally/}
}