PCGOD: Enhancing Object Detection With Synthetic Data for Scarce and Sensitive Computer Vision Tasks

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Walid Remmas, Martin Lints, Jaak Joonas Uudmae
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11009168/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850175107612278784
author Walid Remmas
Martin Lints
Jaak Joonas Uudmae
author_facet Walid Remmas
Martin Lints
Jaak Joonas Uudmae
author_sort Walid Remmas
collection DOAJ
description 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.
format Article
id doaj-art-e2c0a2ee5ca343db8c4d5ec4e1643c14
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-e2c0a2ee5ca343db8c4d5ec4e1643c142025-08-20T02:19:31ZengIEEEIEEE Access2169-35362025-01-0113913259133310.1109/ACCESS.2025.357271911009168PCGOD: Enhancing Object Detection With Synthetic Data for Scarce and Sensitive Computer Vision TasksWalid Remmas0https://orcid.org/0000-0001-8690-0496Martin Lints1Jaak Joonas Uudmae2Research and Development Department, Defsecintel Solutions OÜ, Tallinn, EstoniaResearch and Development Department, Defsecintel Solutions OÜ, Tallinn, EstoniaResearch and Development Department, Defsecintel Solutions OÜ, Tallinn, EstoniaObject 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.https://ieeexplore.ieee.org/document/11009168/Synthetic datadata-augmentationobject detectionautomated labelingAI
spellingShingle Walid Remmas
Martin Lints
Jaak Joonas Uudmae
PCGOD: Enhancing Object Detection With Synthetic Data for Scarce and Sensitive Computer Vision Tasks
IEEE Access
Synthetic data
data-augmentation
object detection
automated labeling
AI
title PCGOD: Enhancing Object Detection With Synthetic Data for Scarce and Sensitive Computer Vision Tasks
title_full PCGOD: Enhancing Object Detection With Synthetic Data for Scarce and Sensitive Computer Vision Tasks
title_fullStr PCGOD: Enhancing Object Detection With Synthetic Data for Scarce and Sensitive Computer Vision Tasks
title_full_unstemmed PCGOD: Enhancing Object Detection With Synthetic Data for Scarce and Sensitive Computer Vision Tasks
title_short PCGOD: Enhancing Object Detection With Synthetic Data for Scarce and Sensitive Computer Vision Tasks
title_sort pcgod enhancing object detection with synthetic data for scarce and sensitive computer vision tasks
topic Synthetic data
data-augmentation
object detection
automated labeling
AI
url https://ieeexplore.ieee.org/document/11009168/
work_keys_str_mv AT walidremmas pcgodenhancingobjectdetectionwithsyntheticdataforscarceandsensitivecomputervisiontasks
AT martinlints pcgodenhancingobjectdetectionwithsyntheticdataforscarceandsensitivecomputervisiontasks
AT jaakjoonasuudmae pcgodenhancingobjectdetectionwithsyntheticdataforscarceandsensitivecomputervisiontasks