Single View Distortion Correction using Semantic Guidance

TL;DR

This paper introduces a novel single-view distortion correction method that leverages semantic guidance and differentiable sampling to correct complex distortions without calibration grids or multiple views.

Contribution

It presents a new approach that uses semantic information and differentiable image sampling to correct highly complex distortions from a single image, bypassing traditional calibration methods.

Findings

Successfully estimates and corrects complex distortions.

Semantic guidance improves undistortion accuracy.

Operates effectively with only one image.

Abstract

Most distortion correction methods focus on simple forms of distortion, such as radial or linear distortions. These works undistort images either based on measurements in the presence of a calibration grid, or use multiple views to find point correspondences and predict distortion parameters. When possible distortions are more complex, e.g. in the case of a camera being placed behind a refractive surface such as glass, the standard method is to use a calibration grid. Considering a high variety of distortions, it is nonviable to conduct these measurements. In this work, we present a single view distortion correction method which is capable of undistorting images containing arbitrarily complex distortions by exploiting recent advancements in differentiable image sampling and in the usage of semantic information to augment various tasks. The results of this work show that our model is able to estimate and correct highly complex distortions, and that incorporating semantic information mitigates the process of image undistortion.