FMAC: a Fair Fiducial Marker Accuracy Comparison Software

2026-01-12

AI Summary

This work addresses the lack of fair and systematic evaluation protocols for pose estimation accuracy among existing fiducial markers. We propose the first physics-based rendering framework for equitable benchmarking, leveraging high-fidelity synthetic images to comprehensively assess the six-degree-of-freedom pose accuracy of multiple mainstream fiducial markers. Our method integrates ray tracing, low-discrepancy sampling, and subpixel edge sampling, while realistically simulating camera lens distortion and optical blur under standard calibration parameters. Extensive experiments reveal significant performance variations across different markers under diverse pose conditions. To support reproducibility and community adoption, we publicly release our standardized evaluation toolkit on GitHub, establishing a reliable benchmark for future research in fiducial-based pose estimation.

Technology Category

Computer Vision: Biometrics, Face, Gesture & PoseIntelligent Robots: State EstimationMachine Learning: Calibration & Uncertainty Quantification

Application Category

Search and Retrieval-Augmented AI: Web evaluation methodologies and metricsSecurity and Privacy: Large-scale security measurementsUser Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

This paper presents a method for carrying fair comparisons of the accuracy of pose estimation using fiducial markers. These comparisons rely on large sets of high-fidelity synthetic images enabling deep exploration of the 6 degrees of freedom. A low-discrepancy sampling of the space allows to check the correlations between each degree of freedom and the pose errors by plotting the 36 pairs of combinations. The images are rendered using a physically based ray tracing code that has been specifically developed to use the standard calibration coefficients of any camera directly. The software reproduces image distortions, defocus and diffraction blur. Furthermore, sub-pixel sampling is applied to sharp edges to enhance the fidelity of the rendered image. After introducing the rendering algorithm and its experimental validation, the paper proposes a method for evaluating the pose accuracy. This method is applied to well-known markers, revealing their strengths and weaknesses for pose estimation. The code is open source and available on GitHub.

Problem

• fiducial markers
• pose estimation
• accuracy comparison
• fair evaluation
• 6 degrees of freedom

Innovation

• fiducial markers
• pose estimation
• physically based rendering
• low-discrepancy sampling
• camera calibration