This paper addresses key aspects of domain randomization in generating synthetic data for manufacturing object detection applications. To this end, we present a comprehensive data generation pipeline that reflects different factors: object characteristics, background, illumination, camera settings, and post-processing. We also introduce the Synthetic Industrial Parts Object Detection dataset (SIP15-OD) consisting of 15 objects from three industrial use cases under varying environments as a test bed for the study, while also employing an industrial dataset publicly available for robotic applications. In our experiments, we present more abundant results and insights into the feasibility as well as challenges of sim-to-real object detection. In particular, we identified material properties, rendering methods, post-processing, and distractors as important factors. Our method, leveraging these, achieves top performance on the public dataset with Yolov8 models trained exclusively on synthetic data; mAP@50 scores of 96.4% for the robotics dataset, and 94.1%, 99.5%, and 95.3% across three of the SIP15-OD use cases, respectively. The results showcase the effectiveness of the proposed domain randomization, potentially covering the distribution close to real data for the applications.
View on arXiv@article{zhu2025_2506.07539,
title={ Domain Randomization for Object Detection in Manufacturing Applications using Synthetic Data: A Comprehensive Study },
author={ Xiaomeng Zhu and Jacob Henningsson and Duruo Li and Pär Mårtensson and Lars Hanson and Mårten Björkman and Atsuto Maki },
journal={arXiv preprint arXiv:2506.07539},
year={ 2025 }
}