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

• URL: http://arxiv.org/abs/2603.13507v1
• Date: Fri, 13 Mar 2026 18:36:44 GMT
• Title: MIRAGE: Model-agnostic Industrial Realistic Anomaly Generation and Evaluation for Visual Anomaly Detection
• Abstract summary: MIRAGE is a fully automated pipeline for realistic anomalous image generation and pixel-level mask creation.<n>Our pipeline accesses any generative model as a black box via API calls.<n>For mask generation at scale, we introduce a lightweight, training-free dual-branch semantic change detection module.
• Score: 11.313360174738465
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Industrial visual anomaly detection (VAD) methods are typically trained on normal samples only, yet performance improves substantially when even limited anomalous data is available. Existing anomaly generation approaches either require real anomalous examples, demand expensive hardware, or produce synthetic defects that lack realism. We present MIRAGE (Model-agnostic Industrial Realistic Anomaly Generation and Evaluation), a fully automated pipeline for realistic anomalous image generation and pixel-level mask creation that requires no training and no anomalous images. Our pipeline accesses any generative model as a black box via API calls, uses a VLM for automatic defect prompt generation, and includes a CLIP-based quality filter to retain only well-aligned generated images. For mask generation at scale, we introduce a lightweight, training-free dual-branch semantic change detection module combining text-conditioned Grounding DINO features with fine-grained YOLOv26-Seg structural features. We benchmark four generation methods using Gemini 2.5 Flash Image (Nano Banana) as the generative backbone, evaluating performance on MVTec AD and VisA across two distinct tasks: (i) downstream anomaly segmentation and (ii) visual quality of the generated images, assessed via standard metrics (IS, IC-LPIPS) and a human perceptual study involving 31 participants and 1,550 pairwise votes. The results demonstrate that MIRAGE offers a scalable, accessible foundation for anomaly-aware industrial inspection that requires no real defect data. As a final contribution, we publicly release a large-scale dataset comprising 500 image-mask pairs per category for every MVTec AD and VisA class, over 13,000 pairs in total, alongside all generation prompts and pipeline code.

Related papers

• Generated Images Are Easier to Forget: A Machine Unlearning Perspective for Synthetic Image Detection [107.62647907393377]
  Large-scale vision models (LVMs) pre-trained on web-scale datasets exhibit exceptional generalization power.<n>We introduce two detection methods: 1) data-free detection, which prunes model parameters to induce unlearning without data access, and 2) data-driven detection, which optimize LVMs to unlearn knowledge tied to generated images.
  arXiv  Detail & Related papers  (2026-08-01T15:33:15Z)
• Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection [53.137651284042434]
  Anomaly inspection plays a vital role in industrial manufacturing, but the scarcity of anomaly samples limits the effectiveness of existing methods.<n>We propose Generate grained Anomaly (GAA), a region-guided, few-shot anomaly image-mask pair generation framework.<n>GAA generates realistic, diverse, and semantically aligned anomalies using only a small number of samples.
  arXiv  Detail & Related papers  (2025-07-13T12:56:59Z)
• SuperAD: A Training-free Anomaly Classification and Segmentation Method for CVPR 2025 VAND 3.0 Workshop Challenge Track 1: Adapt & Detect [17.160007050126403]
  We propose a fully training-free anomaly detection and segmentation method based on feature extraction using the DINOv2 model named SuperAD.<n>Our method achieves competitive results on both test sets of the MVTec AD 2 dataset.
  arXiv  Detail & Related papers  (2025-05-26T09:29:27Z)
• CoSimGen: Controllable Diffusion Model for Simultaneous Image and Mask Generation [1.9393128408121891]
  Existing generative models fail to address the need for high-quality, simultaneous image-mask generation.<n>We propose CoSimGen, a diffusion-based framework for controllable simultaneous image and mask generation.<n>CoSimGen achieves state-of-the-art performance across all datasets, achieving the lowest KID of 0.11 and LPIPS of 0.53 across datasets.
  arXiv  Detail & Related papers  (2025-03-25T13:48:22Z)
• Component-aware Unsupervised Logical Anomaly Generation for Industrial Anomaly Detection [31.27483219228598]
  Anomaly detection is critical in industrial manufacturing for ensuring product quality and improving efficiency in automated processes.<n>Recent generative models often produce unrealistic anomalies increasing false positives, or require real-world anomaly samples for training.<n>We propose ComGEN, a component-aware and unsupervised framework that addresses the gap in logical anomaly generation.
  arXiv  Detail & Related papers  (2025-02-17T11:54:43Z)
• AssemAI: Interpretable Image-Based Anomaly Detection for Manufacturing Pipelines [0.0]
  Anomaly detection in manufacturing pipelines remains a critical challenge, intensified by the complexity and variability of industrial environments. This paper introduces AssemAI, an interpretable image-based anomaly detection system tailored for smart manufacturing pipelines.
  arXiv  Detail & Related papers  (2024-08-05T01:50:09Z)
• Few-shot Online Anomaly Detection and Segmentation [29.693357653538474]
  This paper focuses on addressing the challenging yet practical few-shot online anomaly detection and segmentation (FOADS) task.<n>Under the FOADS framework, models are trained on a few-shot normal dataset, followed by inspection and improvement of their capabilities by leveraging unlabeled streaming data containing both normal and abnormal samples simultaneously.<n>In order to achieve improved performance with limited training samples, we employ multi-scale feature embedding extracted from a CNN pre-trained on ImageNet to obtain a robust representation.
  arXiv  Detail & Related papers  (2024-03-27T02:24:00Z)
• Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection [59.41026558455904]
  We focus on multi-modal anomaly detection. Specifically, we investigate early multi-modal approaches that attempted to utilize models pre-trained on large-scale visual datasets. We propose a Local-to-global Self-supervised Feature Adaptation (LSFA) method to finetune the adaptors and learn task-oriented representation toward anomaly detection.
  arXiv  Detail & Related papers  (2024-01-06T07:30:41Z)
• Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach [49.995833831087175]
  This work proposes a novel method for generating generic Video-temporal PAs by inpainting a masked out region of an image. In addition, we present a simple unified framework to detect real-world anomalies under the OCC setting. Our method performs on par with other existing state-of-the-art PAs generation and reconstruction based methods under the OCC setting.
  arXiv  Detail & Related papers  (2023-11-27T13:14:06Z)
• Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection [122.4894940892536]
  We present a novel self-supervised masked convolutional transformer block (SSMCTB) that comprises the reconstruction-based functionality at a core architectural level. In this work, we extend our previous self-supervised predictive convolutional attentive block (SSPCAB) with a 3D masked convolutional layer, a transformer for channel-wise attention, as well as a novel self-supervised objective based on Huber loss.
  arXiv  Detail & Related papers  (2022-09-25T04:56:10Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• Locally Masked Convolution for Autoregressive Models [107.4635841204146]
  LMConv is a simple modification to the standard 2D convolution that allows arbitrary masks to be applied to the weights at each location in the image. We learn an ensemble of distribution estimators that share parameters but differ in generation order, achieving improved performance on whole-image density estimation.
  arXiv  Detail & Related papers  (2020-06-22T17:59:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.