CVSep 8, 2019

Blind Geometric Distortion Correction on Images Through Deep Learning

arXiv:1909.03459v1103 citations
AI Analysis

This work addresses the need for robust image correction tools in fields like photography and computer vision, though it is incremental as it builds on existing CNN techniques.

The paper tackles the problem of automatically correcting various geometric distortions in single images by introducing a deep learning framework that predicts displacement fields and estimates distortion parameters, achieving superior performance over traditional methods.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes