Blind Geometric Distortion Correction on Images Through Deep Learning

Xiaoyu Li, Bo Zhang, Pedro V. Sander, Jing Liao; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 4855-4864

Abstract


We propose the first general framework to automatically correct different types of geometric distortion in a single input image. Our proposed method employs convolutional neural networks (CNNs) trained by using a large synthetic distortion dataset to predict the displacement field between distorted images and corrected images. A model fitting method uses the CNN output to estimate the distortion parameters, achieving a more accurate prediction. The final corrected image is generated based on the predicted flow using an efficient, high-quality resampling method. Experimental results demonstrate that our algorithm outperforms traditional correction methods, and allows for interesting applications such as distortion transfer, distortion exaggeration, and co-occurring distortion correction.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Li_2019_CVPR,
author = {Li, Xiaoyu and Zhang, Bo and Sander, Pedro V. and Liao, Jing},
title = {Blind Geometric Distortion Correction on Images Through Deep Learning},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}