ProGAN-Based Synthetic Image Generation for Industrial Visual Inspection of Metallic Parts

Hossein Omid Beiki; Sepehr Asgari; Oliver Petrovic; Christian Brecher

cs.CVOct 12, 2026

ProGAN-Based Synthetic Image Generation for Industrial Visual Inspection of Metallic Parts

Authors: Hossein Omid Beiki, Sepehr Asgari, Oliver Petrovic, Christian Brecher

Organizations: Laboratory for Machine Tools and Production Engineering WZL of RWTH, Aachen University, Aachen, Germany

Abstract

Automated visual inspection is essential for efficient repair and recycling of metallic components. AI-based defect detection is a strong fit. However, it is often constrained by scarce, low-diversity training data. To address this gap, we study Generative AI-driven synthetic image generation using Progressive Growing GANs (ProGAN). We implement a ProGAN pipeline with Wasserstein loss and gradient penalty and evaluate key hyperparameters on two public datasets, MVTec AD (metal nut) and MPDD (tube). As a result, training remained stable and the model yielded realistic images. These images can augment training data, improve robustness, and reduce the cost of collecting rare defects.

Synthetic Data Generation

Synthetic data generation creates artificial examples, simulations, and datasets to train, test, or protect machine-learning systems.

See all 627 papers

SynSur: An end-to-end generative pipeline for synthetic industrial surface defect generation and detection
Apr 29, 2026Paul Julius Kühn, Mika Pommeranz, Arjan Kuijper +1Synthetic Data Augmentation Industrial Anomaly Detection
Fraunhofer IGD, 64283 Darmstadt, Germany
Accelerating New Product Introduction for Visual Quality Inspection via Few-Shot Diffusion-Based Defect Synthesis
Apr 22, 2026Serkan Hamdi Güğül, Kemal Levi, Burak AcarSynthetic-to-Real Domain Adaptation Synthetic Data Augmentation
Relimetrics, Inc.
MIRAGE: Model-agnostic Industrial Realistic Anomaly Generation and Evaluation for Visual Anomaly Detection
Mar 13, 2026Jinwei Hu, Francesco Borsatti, Arianna Stropeni +3Synthetic Anomaly Generation Industrial Anomaly Detection
University of Padova, Italy

Apr 29, 2026J/K move · Enter open · S save

SynSur: An end-to-end generative pipeline for synthetic industrial surface defect generation and detection

Paul Julius Kühn, Mika Pommeranz, Arjan Kuijper, Saptarshi Neil Sinha

Fraunhofer IGD, 64283 Darmstadt, Germany

Synthetic Data Augmentation Industrial Anomaly Detection Diffusion-Based Image Generation Synthetic Anomaly Generation

Open paper AskPDF arXiv

The bottleneck in learning-based industrial defect detection is often limited not by model capacity, but by the scarcity of labeled defect data: defects are rare, annotations are expensive, and collecting balanced training sets is slow. We present an end-to-end pipeline for synthetic defect generation and annotation, combining Vision-Language-Model-based prompts, LoRA-adapted diffusion, mask-guided inpainting, and sample filtering with automatic label derivation, and demonstrates the potential of real data with realistic synthetic samples to overcome data scarcity. The evaluation is conducted on, a challenging dataset of pitting defects on ball screw drives, and then on a subset of the Mobile phone screen surface defect segmentation dataset (MSD) dataset to test cross-domain transfer. Beyond downstream detector performance, we analyze key stages of the pipeline, including prompt construction, LoRA selection, and sample filtering with DreamSim and CLIPScore, to understand which synthetic samples are both realistic and useful. Experiments with YOLOv26, YOLOX, and LW-DETR show that synthetic-only training does not replace real data. When combined with real data, synthetic defects can preserve performance and yield modest gains in selected BSData training regimes. The MSD transfer study shows that the overall pipeline structure carries over to a second industrial inspection domain, while also highlighting the importance of domain-specific adaptation and annotation-quality control. Overall, the paper provides an end-to-end assessment of diffusion-based industrial defect synthesis and shows that its strongest value lies in strengthening scarce real datasets rather than substituting for them.

Abstract

Synthetic Data Generation

Explore similar work

SynSur: An end-to-end generative pipeline for synthetic industrial surface defect generation and detection

Accelerating New Product Introduction for Visual Quality Inspection via Few-Shot Diffusion-Based Defect Synthesis

MIRAGE: Model-agnostic Industrial Realistic Anomaly Generation and Evaluation for Visual Anomaly Detection