Semantic scene graph as a foundation for marker-free AR object spatial anchoring

Authors

DOI:

https://doi.org/10.18372/2073-4751.85.21124

Keywords:

augmented reality, semantic scene graph, spatial anchoring, Meta Quest, graph neural network, SLAM, graph attention network, marker-free AR

Abstract

This paper proposes the SG-Anchor algorithm for marker-free spatial anchoring of augmented reality objects on the Meta Quest 3 platform. The method employs a semantic scene graph — a directed weighted graph G=(V,E,W,F,P) where vertices represent semantic objects of the physical environment detected by YOLOv8, and edges encode their spatial-semantic relations. Vertex attributes are formed by concatenating semantic embeddings, geometric bounding box parameters, and statistical stability features. A Graph Attention Network is used for subgraph matching during anchor resolution.

Theoretical analysis demonstrates the method advantage over SLAM-based approaches in scene-change robustness (SRI approx 88-92%) at an expected positioning error of TE approx 2.1 cm.

References

IDC Worldwide Augmented and Virtual Reality Spending Guide, 2024. URL: https://www.idc.com/getdoc.jsp?containerId=IDC_P33199 (дата звернення: 10.01.2025).

Campos C., Elvira R., Rodríguez J. J. G. та ін. ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial, and Multimap SLAM // IEEE Trans. Robotics. 2021. Vol. 37, No. 6. P. 1874-1890.

Engel J., Koltun V., Cremers D. Direct Sparse Odometry // IEEE Trans. Pattern Anal. Mach. Intell. 2018. Vol. 40, No. 3. P. 611-625.

Kato H., Billinghurst M. Marker Tracking and HMD Calibration for a Video-based Augmented Reality Conferencing System // Proc. IWAR. 1999. P. 85-94.

Rosinol A., Gupta A., Abate M. та ін. 3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans // RSS XVI. 2020. DOI: 10.15607/RSS.2020.XVI.079.

Wu Y., Wang S., Hu H. SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation // Proc. ICCV. 2019. P. 7384-7393.

Veličković P., Cucurull G., Casanova A. та ін. Graph Attention Networks // Proc. ICLR. 2018. arXiv:1710.10903.

Meta Spatial Anchors API. Meta Developer Documentation. URL: https://developer.oculus.com/documentation/unity/unity-spatial-anchors-persist-content (дата звернення: 15.01.2025).

Jocher G., Chaurasia A., Qiu J. Ultralytics YOLOv8. 2023. URL: https://github.com/ultralytics/ultralytics (дата звернення: 10.01.2025).

Huang S., Chen Z., Gojcic Z. та ін. Incremental 3D Semantic Scene Graph Prediction from RGB Sequences // Proc. CVPR. 2023. P. 5064-5074.

Downloads

Published

2026-04-28

How to Cite

Kholyavkina, T., & Olishevskyi, B. (2026). Semantic scene graph as a foundation for marker-free AR object spatial anchoring. Problems of Informatization and Control, 1(85). https://doi.org/10.18372/2073-4751.85.21124

Issue

Vol. 1 No. 85 (2026)

Section

Статті

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

The scientific journal adheres to the principles of Open Access and provides free, immediate, and permanent access to all published materials without financial, technical, or legal barriers for readers.

All articles are published in Open Access under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.

Copyright

Authors who publish their works in the journal:

  • retain the copyright to their publications;

  • grant the journal the right of first publication of the article;

  • agree to the distribution of their materials under the CC BY 4.0 license;

  • have the right to reuse, archive, and distribute their works (including in institutional and subject repositories), provided that proper reference is made to the original publication in the journal.