# The Power of Light: Improving Synthetic-to-Real Domain Adaptation through Physically-Based Indirect Illumination

arXiv: https://arxiv.org/abs/2606.22574 · HTML: https://mlsanity.com/paper/2606.22574/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 31 references that are in the map.
- First posted on arXiv 21 Jun 2026.

## Builds on (most cited first, 13 of 13)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization](https://mlsanity.com/paper/1804.06516/) (2018)
- [Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection](https://mlsanity.com/paper/1708.01642/) (2017)
- [Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?](https://mlsanity.com/paper/1610.01983/) (2016)
- [Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing](https://mlsanity.com/paper/1810.08705/) (2018)
- [On Pre-Trained Image Features and Synthetic Images for Deep Learning](https://mlsanity.com/paper/1710.10710/) (2017)
- [Unity Perception: Generate Synthetic Data for Computer Vision](https://mlsanity.com/paper/2107.04259/) (2021)
- [Deflating Dataset Bias Using Synthetic Data Augmentation](https://mlsanity.com/paper/2004.13866/) (2020)
- [Domain Randomization for Object Detection in Manufacturing Applications using Synthetic Data: A Comprehensive Study](https://mlsanity.com/paper/2506.07539/) (2025)
- [Object Detection using Domain Randomization and Generative Adversarial Refinement of Synthetic Images](https://mlsanity.com/paper/1805.11778/) (2018)
- [Small Object Detection for Near Real-Time Egocentric Perception in a Manual Assembly Scenario](https://mlsanity.com/paper/2106.06403/) (2021)

## Abstract (arXiv)

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 ILLUMINTRUCK, 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.