Saved in:
Bibliographic Details
Main Authors: Dubey, Alpana, Kuriakose, Suma Mani, Bhardwaj, Nitish
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.04894
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914023245611008
author Dubey, Alpana
Kuriakose, Suma Mani
Bhardwaj, Nitish
author_facet Dubey, Alpana
Kuriakose, Suma Mani
Bhardwaj, Nitish
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2509_04894
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SynGen-Vision: Synthetic Data Generation for training industrial vision models
Dubey, Alpana
Kuriakose, Suma Mani
Bhardwaj, Nitish
Computer Vision and Pattern Recognition
Machine Learning
I.4
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
title SynGen-Vision: Synthetic Data Generation for training industrial vision models
topic Computer Vision and Pattern Recognition
Machine Learning
I.4
url https://arxiv.org/abs/2509.04894