Book a demo

GAN Synthetic Defect Data Generation — PatSnap Eureka

GAN Synthetic Defect Data Generation — PatSnap Eureka
Explore in Eureka
2026 Technology Landscape

GAN Synthetic Defect Data Generation 2026

Synthetic defect data generation using GANs addresses the chronic scarcity of labeled defect samples in industrial AI. This landscape covers core architectures, application domains, and the 2019–2026 patent record.

2019
Earliest filing year in this dataset
Explore in Eureka
5+
KLA Corporation filings in this dataset
Explore in Eureka
~40%
US-jurisdiction share of patent records in this dataset
Explore in Eureka
~25%
CN-jurisdiction share of patent records in this dataset
Explore in Eureka
Published byPatSnap Insights Team··9 min readVerified by PatSnap Eureka Data
Technology Overview

How GANs Solve the Defect Data Scarcity Problem

GAN-based synthetic defect data generation sits at the intersection of deep generative modeling, computer vision, and industrial quality assurance. Defective products are rare by design in high-quality manufacturing lines, creating severe class imbalance that degrades supervised deep learning classifiers. GANs address this by learning the underlying distribution of defect appearances and generating novel, photorealistic defect samples for downstream model training.

Four core technical clusters define the field: image-to-image translation for defect injection, conditional GANs enabling attribute-controlled synthesis, physics-coupled DCGAN pipelines combining simulation with GAN style transfer, and semiconductor-specific architectures trained on design data. A fifth emerging direction—transformer-based generative pre-trained models—signals a transition beyond classical GAN architectures in the most recent 2025–2026 filings.

Top Assignees by Filing Count — GAN Defect Synthesis (Dataset Snapshot)
Top Assignees by Filing Count: KLA Corporation 5, IBM 5, Applied Materials Israel 4+, Indian Institute of Technology Madras 4, ASML Netherlands 3Horizontal bar chart showing top assignees by estimated filing count in the GAN synthetic defect data generation dataset snapshot. Source: PatSnap Eureka retrieved records 2019–2026.Top Assignees by Filing Count (Dataset Snapshot)KLA Corporation5IBM5Applied Materials Israel4+IIT Madras4↗ Click bars to explore

The earliest records in this dataset date to 2019, with Applied Materials Israel’s foundational WO filing on training-set generation for semiconductor specimen examination and IBM’s coordinate-based GAN for layout pattern synthesis. The 2020–2022 window represents the field’s foundational industrialization phase, with at least 15 distinct patents or literature references identified across US, EP, CN, and WO jurisdictions.

Among retrieved records, KLA Corporation, Applied Materials Israel, and IBM collectively hold the largest share of active semiconductor and layout-domain patents in this dataset. Industrial surface inspection is more fragmented, with Chinese universities and equipment makers accounting for approximately 25% of records in retrieved records.

PatSnap Eureka Filing counts are estimates based on retrieved records in PatSnap Eureka targeted searches covering 2019–2026; this is a dataset snapshot and not a comprehensive industry census.Explore the data ↗
Patent Analytics

Filing Trends and Technology Cluster Distribution

Retrieved records span 2019–2026 across US, CN, WO, EP, IN, and SG jurisdictions. The dataset shows accelerating specialization from 2023 onward and a clear 2025–2026 pivot toward transformer and diffusion architectures.

Patent Filings by Technology Cluster — GAN Defect Synthesis (Dataset Snapshot)

Image-to-image translation and semiconductor-specific GAN clusters account for the largest share of retrieved records in this dataset, reflecting the dominance of wafer inspection and industrial surface defect use cases.

Patent filings by technology cluster: Image-to-Image Translation 12, Semiconductor-Specific GAN 10, Conditional GAN Attribute Control 8, Simulation-Coupled GAN 7, Transformer/Diffusion Frontier 5Horizontal bar chart showing estimated patent and literature record counts per technology cluster in the GAN synthetic defect data generation dataset snapshot, 2019–2026.Records by Technology Cluster (Dataset Snapshot)Image-to-Image Translation12Semiconductor-Specific GAN10Conditional GAN Attribute Control8Simulation-Coupled GAN7Transformer/Diffusion Frontier5↗ Click bars to explore

Filing Activity by Period — GAN Defect Synthesis Dataset (2019–2026)

The 2025–2026 period shows the highest concentration of frontier filings in this dataset, driven by transformer, diffusion model, and 3D-engine-grounded synthesis approaches from NVIDIA, KLA, IMEC, and Applied Materials Israel.

Filing activity by period: 2019 2 records, 2020-2022 15 records, 2023-2024 10 records, 2025-2026 15 recordsVertical bar chart showing estimated count of patent and literature records per filing period in the GAN synthetic defect data generation dataset snapshot, 2019–2026.Filing Activity by Period (Dataset Snapshot)0510152022019152020–2022102023–2024152025–2026↗ Click bars to explore
PatSnap Eureka Record counts per cluster and period are estimates based on retrieved records in PatSnap Eureka targeted searches; they represent a dataset snapshot only.Explore the data ↗
Application Domains

Key Deployment Domains for GAN Defect Synthesis

Retrieved records span four major application domains: industrial surface inspection, semiconductor wafer inspection, non-destructive testing, and medical imaging. Each domain presents distinct data scarcity profiles and generative architecture requirements.

Conditional GAN · Attribute-Controlled Wafer Defect

Semiconductor Wafer Inspection

The most patent-dense specialised sub-domain in this dataset, with KLA Corporation, ASML Netherlands, and Applied Materials Israel holding the majority of semiconductor-specific filings in retrieved records. ASML’s US grant (2024) covers generators conditioned on defect attribute combinations including type, size, location, and strength applied to defect-free inspection images. Applied Materials Israel’s 2026 US filings describe systems generating millions of synthetic fault images at runtime during active wafer fabrication.

Semiconductor Inspection
DCGAN · Image-to-Image Translation · Mask-Guided

Industrial Surface Defect Inspection

The most represented application domain across the dataset, addressing scratches, cracks, dents, and texture anomalies on metal, fabric, and composite surfaces. Shanxi Anshu’s DCGAN pipeline achieves synthesis at approximately 0.15 seconds per image on CPU. Shanghai Zhijing’s mask-guided pix2pix GAN targets grey cloth (raw fabric) defect texture synthesis, while Hefei University of Technology’s 2026 CN filing combines synthetic defect data with adversarial domain adaptation for automotive body surface inspection.

Manufacturing Quality Control
DCGAN · Numerical Simulation · NDT Flaw Data

Non-Destructive Testing (NDT)

Indian Institute of Technology Madras filed across WO (2022), IN, and US (2024) jurisdictions for a system where a numerical simulation model generates NDT datasets with flaw geometrical features, which then train a DCGAN to produce diverse synthetic NDT inspection data covering ultrasonic, radiographic, and eddy-current modalities. This pipeline directly addresses the scarcity of labeled flaw samples in critical infrastructure inspection workflows.

Non-Destructive Testing
GAN · Synthetic Training Data · Lesion Synthesis

Medical Imaging and Surgical AI

Siemens Healthineers AG (US, 2021) filed for GAN-generated synthetic image data training deep learning algorithms in tumor lesion characterization. Digital Surgery Limited (WO, 2024) describes GAN-based synthetic surgical data generation combining with real surgical video to improve training datasets for surgical AI. Nitte University (IN, 2024) filed a mobile-device-based GAN system using pixel-wise and latent space comparison for automated defect identification analogous to lesion detection.

Medical Imaging
PatSnap Eureka Application domain coverage is based on retrieved patent and literature records in PatSnap Eureka targeted searches, 2019–2026.Explore insights ↗
Assignee Landscape

Key Patent Assignees in GAN Defect Synthesis (Retrieved Records)

In this dataset, KLA Corporation and Applied Materials Israel hold the deepest prosecution portfolios in the semiconductor-focused GAN defect synthesis space, with 5+ and 4+ retrieved records respectively. IBM accounts for 5 records spanning physical design layout GAN and feature-combination synthesis in retrieved records, while ASML Netherlands and IIT Madras each contribute 3–4 records in wafer and NDT domains.

Top Assignees by Filing Count — GAN Defect Synthesis (Dataset Snapshot)

Top assignees: KLA Corporation 5, IBM 5, Applied Materials Israel 4, IIT Madras 4, ASML Netherlands 3Horizontal bar chart of top assignees by estimated filing count in the GAN synthetic defect data generation dataset snapshot.KLA Corporation5International Business Machines5Applied Materials Israel Ltd.4+Indian Institute of Technology Madras4ASML Netherlands B.V.3↗ Click bars to explore
Semiconductor GAN Simulation · DefectGPT · Wafer Inspection

KLA Corporation

KLA holds 5+ retrieved records spanning US and WO jurisdictions, with active grants dating from 2021 and pending applications through 2025. Key patents include conditional GANs trained on design data-to-image pairs for wafer specimen simulation (US, 2021; US, 2024) and the DefectGPT transformer-based defect generative pre-trained model filed in both US and WO in April 2025, marking a pivot beyond classical GAN architectures. Patents include both active grants and pending applications targeting the semiconductor wafer inspection domain.

United States
Semiconductor DOI Synthesis · Height-Map Injection · Runtime Generation

Applied Materials Israel Ltd.

Applied Materials Israel holds 4+ retrieved records across WO (2019), US (2020, 2026) jurisdictions, with the foundational WO filing establishing the framework for generating training sets for semiconductor specimen examination. The 2026 US filings cover automated generation and planting of synthetic defects-of-interest (DOIs) enabling millions of synthetic fault images at runtime during wafer fabrication, and a height-map-based 3D defect injection method followed by ML model-based image synthesis. Status includes active grants and pending US applications.

Israel — IL / United States
🔍
Unlock full profiles for 8+ additional assignees in this dataset
Retrieved records include portfolios for ASML Netherlands, IBM, SAP SE, NVIDIA, Samsung SDS, Delta Electronics International, IIT Madras, and Wipro Limited — with jurisdiction breakdowns and technology focus areas available in PatSnap Eureka.
ASML Netherlands wafer GAN SAP SE text-conditioned defect + more
Unlock full assignee analysis →
PatSnap Eureka Filing counts are estimates from retrieved records in PatSnap Eureka targeted searches and represent a dataset snapshot only; they do not reflect total industry filing volumes.Explore players ↗
Emerging Directions

Four Frontier Vectors in GAN Defect Synthesis (2025–2026)

Approximately 15 records published in 2025–2026 in this dataset signal four major shifts: transformer and diffusion displacement of classical GANs, text-conditioned self-supervised generation, 3D-model-grounded photorealistic synthesis, and runtime on-the-fly defect synthesis at scale.

Transformer and Diffusion Models Displacing Classical GANs

KLA Corporation’s DefectGPT (US/WO, 2025) marks the first clear pivot to transformer-based architectures in the semiconductor inspection domain, aligning synthetic defect images with process condition and wafer-level defect distribution. Simultaneously, IMEC VZW’s US filing (2026) applies denoising diffusion probabilistic models (DDPMs) to semiconductor defect image generation. Shenzhen LingYun Vishion Technology Co., Ltd.’s CN filing (2025) uses fine-tuned diffusion models per defect class alongside annotation synthesizers, confirming broad diffusion adoption across both Western and Chinese assignees.

Text-Conditioned and Self-Supervised Defect Generation

SAP SE’s active US and EP grants (2025) for a self-supervised defect generator (SDDG) integrate text embeddings as conditioning inputs, enabling generation of minority-class defect images with minimal or no defect examples. IBM’s 2021 US patent for text-encoded feature combination conditioning enables generation of defect images for previously unseen feature combinations. These filings together signal convergence of large language model embeddings with defect synthesis pipelines, creating a capability gap for organizations reliant on purely visual conditioning.

🔒
Access full analysis of all 4 emerging vectors and white-space mapping
Detailed claim-level analysis of KLA DefectGPT, IMEC DDPM, SAP SE SDDG, and NVIDIA 3D synthesis filings is available in PatSnap Eureka, including FTO risk indicators and citation network mapping.
IMEC DDPM advanced nodeNVIDIA 3D defect severity+ more
Unlock full analysis →
PatSnap Eureka Emerging direction signals are based on approximately 15 records published in 2025–2026 in this dataset and represent a snapshot of recent innovation only.Explore emerging trends ↗
Architecture Comparison

Classical GAN vs. Transformer/Diffusion Architectures for Defect Synthesis

Click any row to explore further.

DimensionClassical GAN ArchitecturesTransformer / Diffusion Architectures
Representative FilingsKLA GAN specimen simulation (US, 2021); ASML conditional wafer defect GAN (US, 2024); Delta Electronics cycle GAN (SG, 2022)KLA DefectGPT transformer (US/WO, 2025); IMEC VZW DDPM for advanced node (US, 2026); Shenzhen LingYun diffusion per-class (CN, 2025)
Core MechanismGenerator-discriminator adversarial training; image-to-image translation or conditional attribute injectionTransformer autoregressive token generation (DefectGPT) or iterative denoising via DDPM for image synthesis
Conditioning InputsDesign data, defect attribute vectors (type, size, location, strength), spatial masks, Poisson blendingProcess condition metadata, wafer-level defect distribution, text embeddings (SAP SE SDDG), per-class fine-tuning
Training Data RequirementRequires paired or unpaired defect/non-defect image sets; class imbalance addressed via augmentation loopsSAP SE SDDG targets minority class generation with minimal defect examples; diffusion models leverage pre-training
Synthesis SpeedShanxi Anshu DCGAN achieves ~0.15 seconds per image on CPU; Applied Materials Israel targets millions of images at runtimeDiffusion models typically slower at inference; transformer models’ runtime speed not specified in retrieved records
Jurisdiction ActivityDominant in US, CN, WO, EP, IN, SG filing records 2019–2024Emerging primarily in US and WO records 2025–2026; CN diffusion filings appearing from Shenzhen assignees
3D IntegrationChangzhou Weiyi (2023): Blender + pix2pixHD; Raytheon (2024): 3D engine for ATR datasetNVIDIA (2026): 3D model-based system with configurable lighting, environment, and severity levels
Patent Status (dataset)Mix of active grants (KLA US 2021, ASML US 2024) and pending applications across jurisdictionsPredominantly pending applications (KLA DefectGPT US/WO 2025, IMEC US 2026, Applied Materials Israel US 2026)
PatSnap Eureka Comparison is based on patent and literature records retrieved in PatSnap Eureka targeted searches; it represents a dataset snapshot and not a comprehensive architectural survey.Compare in Eureka ↗
Frequently asked questions

Frequently Asked Questions: GAN Synthetic Defect Data Generation

Still have questions? PatSnap Eureka can answer them instantly from patent and research data.Ask Eureka ↗
PatSnap Eureka

Analyse GAN Defect Synthesis Patents and Find White Space

Join 18,000+ innovators using PatSnap Eureka to generate reports like this one for any technology area.

Data and insights on this page are based on a limited patent and literature dataset and are for reference only. Figures may not represent the complete technology landscape.

Powered by PatSnap Eureka
Link copied to clipboard

Eureka built for innovation research

Eureka built for research
Domain-specific AI agents for IP, Engineering, Life Sciences, and Materials
Patents, Scientific Literature, Compounds & More Unified in One Platform
Ask, Research, Solve, Draft, and Validate Your Work from Weeks to Minutes
Try it for Free

Help us improve this page

Found incorrect or outdated information? Let us know and we'll get it fixed.