CLARIS: Control-based language-guided realistic imperfection synthesis
Authors:
Open Access
- 9 April 2026
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Abstract
Automated vision inspection is vital in modern manufacturing, but advanced processes with high yield rates cause a severe data imbalance: abundant normal data and scarce defective data. To overcome this, we propose CLARIS (Control-based Language-guided Realistic Imperfection Synthesis), a novel framework combining natural language semantic flexibility with 3D structural constraints to generate physically consistent, high-quality defect images. CLARIS utilizes a Vision-Language Model (VLM) to interpret user instructions and input images, dynamically generating tailored text prompts and defect masks. Subsequently, ControlNet ensures the synthesized defects adhere to the object’s physical shape and surface curvature by explicitly applying normal maps as constraints. Furthermore, Textual Inversion (TI) and Low-Rank Adaptation (LoRA) are employed to efficiently learn and reflect the unique visual characteristics of specific defects using minimal parameters. Evaluated on the 15 categories of the MVTec Anomaly Detection (MVTec AD) dataset, the framework achieved an average Kernel Inception Distance (KID) of 11.07, Inception Score (IS) of 1.63, and intra-cluster pairwise LPIPS distance (IC-LPIPS) of 0.27.Keywords
Funding Information
- Institute of Information & Communications Technology Planning & Evaluation(IITP)-ICT Creative Consilience Program (IITP-2025-RS-2020-II201821)
- Institute of Information & Communications Technology Planning & Evaluation(IITP)-ICT Creative Consilience Program (IITP-2025-RS-2020-II201821)
This publication has 17 references indexed in Scilit:
- DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspection2025
- InstructPix2Pix: Learning to Follow Image Editing Instructions2023
- GLIGEN: Open-Set Grounded Text-to-Image Generation2023
- Towards Total Recall in Industrial Anomaly Detection2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- CutPaste: Self-Supervised Learning for Anomaly Detection and Localization2021
- The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly DetectionInternational Journal of Computer Vision, 2021
- Analyzing and Improving the Image Quality of StyleGAN2020
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- Rethinking the Inception Architecture for Computer Vision2016