Single Image Automatic Radial Distortion Compensation Using Deep Convolutional Network

TL;DR

This paper introduces a deep learning-based method for real-time automatic radial distortion correction in single images, particularly suited for sports broadcast footage with complex lenses and uncalibrated cameras.

Contribution

It proposes a novel deep convolutional neural network approach that accurately estimates radial distortion coefficients from a single image in real-time, addressing challenges in uncalibrated and complex lens scenarios.

Findings

Achieves real-time performance in distortion correction.

Accurately estimates higher-order distortion coefficients.

Effective on sports broadcast footage with complex lenses.

Abstract

In many computer vision domains, the input images must conform with the pinhole camera model, where straight lines in the real world are projected as straight lines in the image. Performing computer vision tasks on live sports broadcast footage imposes challenging requirements where the algorithms cannot rely on a specific calibration pattern must be able to cope with unknown and uncalibrated cameras, radial distortion originating from complex television lenses, few visual clues to compensate distortion by, and the necessity for real-time performance. We present a novel method for single-image automatic lens distortion compensation based on deep convolutional neural networks, capable of real-time performance and accuracy using two highest-order coefficients of the polynomial distortion model operating in the application domain of sports broadcast. Keywords: Deep Convolutional Neural Network, Radial Distortion, Single Image Rectification