# SynGen-Vision: Synthetic Data Generation for training industrial vision models

arXiv: https://arxiv.org/abs/2509.04894 · HTML: https://mlsanity.com/paper/2509.04894/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 19 references that are in the map.
- First posted on arXiv 5 Sep 2025.

## Builds on (most cited first, 6 of 6)

- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [Domain Adaptive Text Style Transfer](https://mlsanity.com/paper/1908.09395/) (2019)
- [Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition](https://mlsanity.com/paper/2004.02684/) (2020)
- [Controllable Image Synthesis of Industrial Data Using Stable Diffusion](https://mlsanity.com/paper/2401.03152/) (2024)

## Built on by (most cited first, 1 of 1)

- [Action-guided generation of 3D functionality segmentation data](https://mlsanity.com/paper/2511.23230/) (2025)

## Abstract (arXiv)

We propose an approach to generate synthetic data to train computer vision (CV) models for industrial wear and tear detection. Wear and tear detection is an important CV problem for predictive maintenance tasks in any industry. However, data curation for training such models is expensive and time-consuming due to the unavailability of datasets for different wear and tear scenarios. Our approach employs a vision language model along with a 3D simulation and rendering engine to generate synthetic data for varying rust conditions. We evaluate our approach by training a CV model for rust detection using the generated dataset and tested the trained model on real images of rusted industrial objects. The model trained with the synthetic data generated by our approach, outperforms the other approaches with a mAP50 score of 0.87. The approach is customizable and can be easily extended to other industrial wear and tear detection scenarios