[
    {
        "id": "osp-20446",
        "type": "article-journal",
        "title": "From Unity Simulation to Diffusion-Based Augmentation: Quantifying Dataset Balance for Robust Object Detection",
        "author": [
            {
                "family": "Benkedadra",
                "given": "Mohamed"
            },
            {
                "family": "Saoudi",
                "given": "Aissa"
            },
            {
                "family": "Gloesener",
                "given": "Maxime"
            },
            {
                "family": "Mahmoudi",
                "given": "Sidi Ahmed"
            },
            {
                "family": "Mancas",
                "given": "Matei"
            }
        ],
        "URL": "https://omanscience.com/en/articles/from-unity-simulation-to-diffusion-based-augmentation-quantifying-dataset-balance-for-robust-object-detection",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "DOI": "10.1145/3787256.3787261",
        "abstract": "Modern computer vision models achieve high accuracy when trained on large-scale annotated datasets. In critical domains such as construction safety monitoring, data collection is costly, hazardous, and ethically constrained. This paper presents a systematic study comparing two complementary data generation paradigms, (1) Unity Simulation-based rendering and (2) Controllable Diffusion-based generation (CIA), for object detection under real data-scarce conditions. A unified experimental framework enables controlled dataset mixing across real, simulated, and generative sources, while maintaining identical model and training settings. Quantitative evaluation using Precision, Recall, mAP, and custom $Δ$-metrics, reveals that neither simulation nor generative augmentation alone achieves optimal transferability. Unity-only training yields an mAP@0.5 drop of $-50\\%$ relative to real data, while CIA-only training shows a milder $-16.5\\%$ degradation. Hybrid compositions significantly improve performance, with the 90\\% real + 10\\% Unity configuration achieving the best overall mAP@0.5 of $62.68\\%$ ($+7.64\\%$ over baseline), and the 90\\% real + 10\\% CIA configuration maximizing precision at $74.45\\%$. Results demonstrate that limited synthetic inclusion enhances generalization, while excessive substitution induces domain drift."
    }
]