From Unity Simulation to Diffusion-Based Augmentation: Quantifying Dataset Balance for Robust Object Detection

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 $\mathrm{\Delta }$-metrics, reveals that neither simulation nor generative augmentation alone achieves optimal transferability. Unity-only training yields an mAP@0.5 drop of $-50\mathrm{\%}$ relative to real data, while CIA-only training shows a milder $-16.5\mathrm{\%}$ degradation. Hybrid compositions significantly improve performance, with the 90% real + 10% Unity configuration achieving the best overall mAP@0.5 of $62.68\mathrm{\%}$ ($+7.64\mathrm{\%}$ over baseline), and the 90% real + 10% CIA configuration maximizing precision at $74.45\mathrm{\%}$. Results demonstrate that limited synthetic inclusion enhances generalization, while excessive substitution induces domain drift.