Hong, Ilkwon Ha, Junhyoung 2025-03-24T01:00:12Z 2025-03-24T01:00:12Z 2025-03-19 2025-03 https://pubs.kist.re.kr/handle/201004/152102 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. English Institute of Electrical and Electronics Engineers Inc. Generative Adversarial Networks for Solving Hand-Eye Calibration Without Data Correspondence Article 10.1109/LRA.2025.3533470 1 IEEE Robotics and Automation Letters, v.10, no.3, pp.2494 - 2501 IEEE Robotics and Automation Letters 10 3 2494 2501 N scie scopus 001411912800004 2-s2.0-85216346016 Robotics Robotics Article SIMULTANEOUS ROBOT-WORLD Calibration Generative adversarial networks Training Generators Probability density function Parameter estimation Robots Noise measurement Mathematical models Deep learning Calibration without data correspondence generative adversarial networks (GANs) hand-eye calibration