Generative Adversarial Networks for Solving Hand-Eye Calibration without Data Correspondence

TL;DR

This paper introduces a novel GAN-based approach for solving hand-eye calibration problems without requiring data correspondence, framing calibration as a distribution matching task.

Contribution

It applies GANs to calibration problems lacking data correspondence, offering a new perspective and method for complex calibration tasks.

Findings

Effective calibration without data correspondence

Applicable to complex calibration scenarios

Demonstrates benefits over traditional methods

Abstract

In this study, we rediscovered the framework of generative adversarial networks (GANs) as a solver for calibration problems without data correspondence. When data correspondence is not present or loosely established, the calibration problem becomes a parameter estimation problem that aligns the two data distributions. This procedure is conceptually identical to the underlying principle of GAN training in which networks are trained to match the generative distribution to the real data distribution. As a primary application, this idea is applied to the hand-eye calibration problem, demonstrating the proposed method's applicability and benefits in complicated calibration problems.