The Power of Light: Improving Synthetic-to-Real Domain Adaptation through Physically-Based Indirect Illumination
For practitioners in industrial automation using synthetic data for object detection, this provides actionable guidelines to improve domain adaptation.
This paper studies how lighting and background complexity in synthetic data affect object detection performance, showing that complex indirect lighting with domain-relevant backgrounds reduces domain gap and false positives while accelerating convergence compared to direct lighting.
While synthetic data generation resolves the manual labeling bottleneck in computer vision, minimizing the syn-to-real domain gap requires optimizing rendering variables. This paper presents a systematic study analyzing the impact of lighting configurations and background complexity on object detection performance. We introduce SmartSDG, an automated, reproducible pipeline built on NVIDIA Isaac Sim using Physically-Based Shading (PBS), alongside ILLUM\_INTRUCK, a new multi-object industrial benchmark dataset. Through 18 controlled experiments utilizing a state-of-the-art YOLOv12 framework, we demonstrate that complex, indirect lighting configurations paired with domain-relevant background variability significantly increase visual cue richness. Our quantitative findings show that avoiding direct specular peaks preserves crucial surface textures, mitigates the domain gap, reduces false positives, and accelerates model convergence compared to using conventional direct-light synthetic data. Ultimately, we provide actionable virtual scene design guidelines to maximize object detection robustness in industrial automation.