# A Synthetic Dataset for Manometry Recognition in Robotic Applications

arXiv: https://arxiv.org/abs/2508.17468 · HTML: https://mlsanity.com/paper/2508.17468/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 41 references that are in the map.
- First posted on arXiv 24 Aug 2025.

## Builds on (most cited first, 8 of 8)

- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [CAD2RL: Real Single-Image Flight without a Single Real Image](https://mlsanity.com/paper/1611.04201/) (2016)
- [Understanding Domain Randomization for Sim-to-real Transfer](https://mlsanity.com/paper/2110.03239/) (2021)
- [BlenderProc](https://mlsanity.com/paper/1911.01911/) (2019)
- [Unity Perception: Generate Synthetic Data for Computer Vision](https://mlsanity.com/paper/2107.04259/) (2021)
- [How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?](https://mlsanity.com/paper/1903.11774/) (2019)

## Abstract (arXiv)

This paper addresses the challenges of data scarcity and high acquisition costs in training robust object detection models for complex industrial environments, such as offshore oil platforms. Data collection in these hazardous settings often limits the development of autonomous inspection systems. To mitigate this issue, we propose a hybrid data synthesis pipeline that integrates procedural rendering and AI-driven video generation. The approach uses BlenderProc to produce photorealistic images with domain randomization and NVIDIA's Cosmos-Predict2 to generate physically consistent video sequences with temporal variation. A YOLO-based detector trained on a composite dataset, combining real and synthetic data, outperformed models trained solely on real images. A 1:1 ratio between real and synthetic samples achieved the highest accuracy. The results demonstrate that synthetic data generation is a viable, cost-effective, and safe strategy for developing reliable perception systems in safety-critical and resource-constrained industrial applications.