# SynthPID: P&ID digitization from Topology-Preserving Synthetic Data

arXiv: https://arxiv.org/abs/2604.16513 · HTML: https://mlsanity.com/paper/2604.16513/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 15 Apr 2026.

## Builds on (most cited first, 9 of 9)

- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Solving Rubik's Cube with a Robot Hand](https://mlsanity.com/paper/1910.07113/) (2019)
- [Character Region Awareness for Text Detection](https://mlsanity.com/paper/1904.01941/) (2019)
- [Relationformer: A Unified Framework for Image-to-Graph Generation](https://mlsanity.com/paper/2203.10202/) (2022)
- [EGTR: Extracting Graph from Transformer for Scene Graph Generation](https://mlsanity.com/paper/2404.02072/) (2024)
- [Digitize-PID: Automatic Digitization of Piping and Instrumentation Diagrams](https://mlsanity.com/paper/2109.03794/) (2021)
- [From Engineering Diagrams to Graphs: Digitizing P&IDs with Transformers](https://mlsanity.com/paper/2411.13929/) (2024)

## Abstract (arXiv)

Automating the digitization of Piping and Instrumentation Diagrams (P&IDs) into structured process graphs would unlock significant value in plant operations, yet progress is bottlenecked by a fundamental data problem: engineering drawings are proprietary, and the entire community shares a single public benchmark of just 12 annotated images. Prior attempts at synthetic augmentation have fallen short because template-based generators scatter symbols at random, producing graphs that bear little resemblance to real process plants and, accordingly, yield only approximately 33% edge detection accuracy under synth-only training. We argue the failure is structural rather than visual and address it by introducing SynthPID, a corpus of 665 synthetic P&IDs whose pipe topology is seeded directly from real drawings. Paired with a patch-based Relationformer adapted for high-resolution diagrams, a model trained on SynthPID alone achieves 63.8 +/- 3.1% edge mAP on PID2Graph OPEN100 without seeing a single real P&ID during training, closing within 8 pp of the real-data oracle. These gains hold up under a controlled comparison against the template-based regime, confirming that generation quality drives performance rather than model choice. A scaling study reveals that gains flatten beyond roughly 400 synthetic images, pointing to seed diversity as the binding constraint.