# DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspection

arXiv: https://arxiv.org/abs/2503.13985 · HTML: https://mlsanity.com/paper/2503.13985/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 30 of its 40 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing](https://mlsanity.com/paper/2304.08465/) (2023)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [CutPaste: Self-Supervised Learning for Anomaly Detection and Localization](https://mlsanity.com/paper/2104.04015/) (2021)
- [DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection](https://mlsanity.com/paper/2108.07610/) (2021)
- [Blended Latent Diffusion](https://mlsanity.com/paper/2206.02779/) (2022)
- [SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2207.14315/) (2022)
- [Deep Semi-Supervised Anomaly Detection](https://mlsanity.com/paper/1906.02694/) (2019)
- [Few-shot Image Generation via Cross-domain Correspondence](https://mlsanity.com/paper/2104.06820/) (2021)
- [AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model](https://mlsanity.com/paper/2312.05767/) (2023)
- [Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection](https://mlsanity.com/paper/2103.15158/) (2021)
- [Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation](https://mlsanity.com/paper/2303.02389/) (2023)
- [RealFill: Reference-Driven Generation for Authentic Image Completion](https://mlsanity.com/paper/2309.16668/) (2023)
- [Prototypical Residual Networks for Anomaly Detection and Localization](https://mlsanity.com/paper/2212.02031/) (2022)
- [CLiC: Concept Learning in Context](https://mlsanity.com/paper/2311.17083/) (2023)
- [Personalized Residuals for Concept-Driven Text-to-Image Generation](https://mlsanity.com/paper/2405.12978/) (2024)

## Built on by (most cited first, 13 of 13)

- [One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Control](https://mlsanity.com/paper/2603.18093/) (2026)
- [MAGIC: Few-Shot Mask-Guided Anomaly Inpainting with Prompt Perturbation, Spatially Adaptive Guidance, and Context Awareness](https://mlsanity.com/paper/2507.02314/) (2025)
- [Unsupervised Multi-View Visual Anomaly Detection via Progressive Homography-Guided Alignment](https://mlsanity.com/paper/2511.18766/) (2025)
- [Advancing Metallic Surface Defect Detection via Anomaly-Guided Pretraining on a Large Industrial Dataset](https://mlsanity.com/paper/2509.18919/) (2025)
- [UniADC: A Unified Framework for Anomaly Detection and Classification](https://mlsanity.com/paper/2511.06644/) (2025)
- [DeltaDeno: Zero-Shot Anomaly Generation via Delta-Denoising Attribution](https://mlsanity.com/paper/2511.16920/) (2025)
- [Synthesis4AD: Synthetic Anomalies are All You Need for 3D Anomaly Detection](https://mlsanity.com/paper/2604.04658/) (2026)
- [Large-Scale Universal Defect Generation: Foundation Models and Datasets](https://mlsanity.com/paper/2604.08915/) (2026)
- [SynSur: An end-to-end generative pipeline for synthetic industrial surface defect generation and detection](https://mlsanity.com/paper/2604.26633/) (2026)
- [OSAGEN: Object-Aware Mask Priors and Multistage Decoupled Diffusion for Industrial Anomaly Generation](https://mlsanity.com/paper/2607.29533/) (2026)
- [Spatial Attention Supervision for Defect Localization: Exploiting Ground-Truth Masks as Training Signal in Diffusion-Augmented Defect Detection](https://mlsanity.com/paper/2609.06232/) (2026)
- [FLASH: A "Generate Once, Synthesize Many" Framework for Synthetic Anomaly Generation in Industrial Anomaly Detection](https://mlsanity.com/paper/2609.37314/) (2026)
- [CORE: Contrast-and-Reflect for Self-Supervised Prompt Optimization in Anomaly Synthesis](https://mlsanity.com/paper/2610.19610/) (2026)

## Abstract (arXiv)

Developing effective visual inspection models remains challenging due to the scarcity of defect data. While image generation models have been used to synthesize defect images, producing highly realistic defects remains difficult. We propose DefectFill, a novel method for realistic defect generation that requires only a few reference defect images. It leverages a fine-tuned inpainting diffusion model, optimized with our custom loss functions incorporating defect, object, and attention terms. It enables precise capture of detailed, localized defect features and their seamless integration into defect-free objects. Additionally, our Low-Fidelity Selection method further enhances the defect sample quality. Experiments show that DefectFill generates high-quality defect images, enabling visual inspection models to achieve state-of-the-art performance on the MVTec AD dataset.