English

Blind Geometric Distortion Correction on Images Through Deep Learning

Computer Vision and Pattern Recognition 2019-09-10 v1

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.

Keywords

Cite

@article{arxiv.1909.03459,
  title  = {Blind Geometric Distortion Correction on Images Through Deep Learning},
  author = {Xiaoyu Li and Bo Zhang and Pedro V. Sander and Jing Liao},
  journal= {arXiv preprint arXiv:1909.03459},
  year   = {2019}
}

Comments

10 pages, 11 figures, published in CVPR 2019

R2 v1 2026-06-23T11:08:56.484Z