Distortion Estimation Through Explicit Modeling of the Refractive Surface

TL;DR

This paper introduces a method for estimating distortion caused by refractive surfaces in camera systems by explicitly modeling the refractive geometry and using neural networks for parameter estimation, improving calibration accuracy.

Contribution

It presents a novel approach that models the refractive surface explicitly and employs neural networks for precise distortion estimation in calibration.

Findings

Effective distortion correction on synthetic data

Successful application to real-world images

Improved calibration accuracy

Abstract

Precise calibration is a must for high reliance 3D computer vision algorithms. A challenging case is when the camera is behind a protective glass or transparent object: due to refraction, the image is heavily distorted; the pinhole camera model alone can not be used and a distortion correction step is required. By directly modeling the geometry of the refractive media, we build the image generation process by tracing individual light rays from the camera to a target. Comparing the generated images to their distorted - observed - counterparts, we estimate the geometry parameters of the refractive surface via model inversion by employing an RBF neural network. We present an image collection methodology that produces data suited for finding the distortion parameters and test our algorithm on synthetic and real-world data. We analyze the results of the algorithm.