PCGOD: Enhancing Object Detection With Synthetic Data for Scarce and Sensitive Computer Vision Tasks
IEEE Access · 2025 · 13 · 91325-91333
DOI: 10.1109/access.2025.3572719 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Walid Remmas und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Defence Fund Project Frugal and Robust AI for Defence Advanced Intelligence.
Abstract (Originalsprache)
Object detection models rely on large-scale, high-quality annotated datasets, which are often expensive, scarce, or restricted due to privacy concerns. Synthetic data generation has emerged as an alternative, yet existing approaches have limitations: generative models lack structured annotations and precise spatial control, while game-engine-based datasets suffer from inaccuracies due to 3D bounding box projections, limited scene diversity, and poor handling of articulated objects. We propose PCGOD, an Unreal Engine-based framework that combines photorealistic rendering with comprehensive domain randomization to bridge the synthetic-to-real (sim2real) domain gap. PCGOD employs a marker-based extremity projection method that places markers at key points on object geometries and projects only visible markers to create tight-fitting bounding boxes. For articulated objects, our approach dynamically tracks skeletal pose changes, ensuring annotations adapt to varied configurations. The framework addresses sim2real transfer through six-dimensional randomization: background environments, model textures and poses, landscape textures, weather conditions, camera perspectives, and procedural scene composition. Evaluations using YOLOv11 and Salience-DETR in an object detection task demonstrate that our marker-based approach achieves up to 41.61% improvement in annotation accuracy over conventional methods. Models trained with just 10% real data supplemented by our synthetic data achieve over 80% of the performance of models trained on 100% real data. Moreover, mixed datasets containing 25% synthetic and 75% real data outperform pure real-data training by up to 5.1%. These results confirm that our approach significantly enhances synthetic data utility for object detection, offering an effective solution for domains with limited training data availability.
Förderung
- European Defence Fund Project Frugal and Robust AI for Defence Advanced Intelligence
Zitieren
APA
Remmas, W., Lints, M., & Uudmäe, J. J. (2025). PCGOD: Enhancing Object Detection With Synthetic Data for Scarce and Sensitive Computer Vision Tasks. IEEE Access, 13, 91325-91333. https://doi.org/10.1109/access.2025.3572719
Vancouver
Remmas W, Lints M, Uudmäe JJ. PCGOD: Enhancing Object Detection With Synthetic Data for Scarce and Sensitive Computer Vision Tasks. IEEE Access. 2025;13:91325-91333. doi:10.1109/access.2025.3572719
BibTeX
@article{Remmas2025,
author = {Remmas, Walid and Lints, Martin and Uudmäe, Jaak Joonas},
title = {PCGOD: Enhancing Object Detection With Synthetic Data for Scarce and Sensitive Computer Vision Tasks},
journal = {IEEE Access},
year = {2025},
volume = {13},
pages = {91325--91333},
doi = {10.1109/access.2025.3572719}
}
EUVIMED