FLASH: A "Generate Once, Synthesize Many" Framework for Synthetic Anomaly Generation in Industrial Anomaly Detection

Abhay Kumar Das; Rajesh Gangireddy; Ashwin Vaidya; Samet Akcay

cs.CVSep 29, 2026

FLASH: A "Generate Once, Synthesize Many" Framework for Synthetic Anomaly Generation in Industrial Anomaly Detection

Authors: Abhay Kumar Das, Rajesh Gangireddy, Ashwin Vaidya, Samet Akcay

Organizations: Silicon University, Bhubaneswar, India · Intel

Abstract

Synthetic anomaly generation helps expand industrial anomaly datasets when real defects are scarce or unavailable. Existing approaches lie at two extremes: procedural approaches are fast but struggle to represent complex anomalies, while generative approaches produce diverse defects but require costly per-sample generation. We present FLASH, a framework that decouples defect generation from anomaly synthesis under a ``generate once, synthesize many'' paradigm. Given only normal images, FLASH uses Vision-Language Model (VLM) guidance and an image-generation model to produce a small set of defect images, from which it extracts, validates, and banks reusable defect patches. For synthesis of anomalous images, Object Boundary Suppression (OBS) first identifies the probable foreground object-aware region of the host image, while Multi-Resolution Spectral Pyramid (MRSP) noise generates diverse, size-controllable masks that determine the defect location and spatial extent. It then composes a large and diverse synthetic anomalous image set by localizing the defect region, sampling size-controllable placement masks and seamlessly blending retrieved defects onto new defect-free images without further need for image generation. Experiments on the MVTec AD 2 dataset show that FLASH-generated anomalies nearly close the calibration gap on real defects, reaching 78.1% image-level F1 against an 83.6% real-anomaly upper bound and providing the most consistent calibration transfer across detectors among procedural and generative alternatives. Moreover, FLASH synthesizes anomalies more than 11.95x faster than per-sample generative approaches.

Figures & tables

Figure 1 : Five-stage FLASH architecture. Stages 1–3 generate, extract, validate, and store reusable defects, while Stages 4–5 localize and synthesize retrieved defects onto separate normal host images.

Figure 2 : DiffMask-based defect extraction from registered normal and generated anomaly images.

Figure 3 : Qualitative results across all eight MVTec AD 2 categories, illustrating the end-to-end FLASH pipeline.

Model	Real	Perlin	AnoStyler	FLASH (Ours)
PaDiM	80.37	69.41	62.37	79.11
PatchCore	82.46	67.50	43.02	74.64
AnomalyDINO	81.47	62.19	49.85	77.05
Dinomaly	81.81	60.42	55.37	77.51
SuperADD	83.64	79.12	64.36	78.13

Table 1 : (a) Image-level F1 and (b) pixel-level F1 scores (%) averaged across categories of the MVTec AD 2.

Category	Real	Perlin	AnoStyler	FLASH (Ours)
Can	0.02	0.01	0.00	0.00
Fabric	78.36	18.57	44.30	69.06
Fruit Jelly	56.07	40.02	55.93	55.57
Rice	58.75	6.21	25.36	51.90
Sheet Metal	35.87	2.53	7.79	7.39
Vial	57.05	56.46	46.63	39.41

Table 2 : Per-category pixel-level F1 scores (%) using SuperADD.

Method	$I_{a}$ Gen. (s/image)	$I_{syn}$ Gen. (ms/image)	Total (s/category)
Perlin	–	14.4	1.3
AnoStyler	–	14,982.1	1,348.1
FLASH (Ours)	15	586.2	112.8

Table 3 : Estimated generation time for

I_{a}

and

I_{syn}

. Total (s/category) indicates the total time taken to generate the synthetic images for a category of MVTec AD 2.

Hyperparameter	Value	Purpose
Synthesis resolution	$1024$ px	Provides sufficient spatial support for localized defects and blending.
DiffMask context expansion	$1.8$	Retains surrounding substrate context around the recovered defect.
Minimum defect region	$500$ px	Suppresses small reconstruction artifacts during defect extraction.
Defect contrast threshold	$\Delta E=6.0$	Filters weak defect evidence using perceptual color difference.
MRSP noise scale	$14$	Controls the characteristic spatial scale of the placement field.
MRSP octaves	$6$	Provides multi-resolution spatial structure for defect placement.

Table 4: Principal hyperparameters governing defect extraction, object-aware placement, adaptive defect sizing, and hybrid compositing. The configuration is fixed across categories after development.

Component	Configuration
Anomalib	2.5.2
Python	3.13
PyTorch	2.13.0 (CUDA 13.0)
PyTorch Lightning	2.6.5
TorchMetrics	1.9.0
Torchvision	0.28.0

Table 5 : Software and hardware environment used for all experiments.

Figure 4 : Joint comparison of noise primitives in terms of generation time, EMD, and calibrated

F_{1}

. (a) Calibrated

F_{1}

on the real test set versus EMD to the real anomaly-score distribution; lower EMD and higher

F_{1}

are preferred, with the horizontal axis reversed accordingly. (b) Noise-generation time on a logarithmic scale (measured on images at

224\times 224

resolution), where lower values are preferred. Marker shapes distinguish single-octave and six-octave fBm configurations, while MRSP is highlighted as the proposed primitive. MRSP provides a favorable trade-off among computational cost, similarity to real anomaly-score distributions, and calibration transfer.

Configuration	Value	Purpose
Random seeds	$\{0,1,2\}$	Provides repeated paired evaluations under controlled stochastic variation.
VLM	Qwen2.5-VL-7B-Instruct	Used for semantic anomaly specification and defect validation.
Synthetic anomalies	$90$ / category / seed	Fixed synthetic calibration budget.
SuperADD backbone	DINOv3 ViT-H/16+	Frozen representation used across all evaluation settings.
Patch-feature cap	$8000$	Fixed memory-bank capacity across evaluation settings.

Table 6: Fixed corpus and downstream evaluation configuration used in the reported experiments.

Figure 5 : MRSP ablation at the MVTec AD 2 operating point. Placement masks are evaluated across spectral exponent $\alpha$ and pyramid levels $L$ at fixed coverage $c=0.018$ . The selected configuration, $\alpha=1.5$ and $L=6$ , provides a coherent placement region while avoiding excessive fragmentation or over-smoothing.

Figure 6 : Construction of the object-aware placement mask $M_{f}$ for Can, Fabric, Fruit Jelly, and Rice. Each row shows the MRSP field, its restriction to the object region $\Omega$ , thresholded response, retained largest connected component, and seed-dependent placement regions.

Figure 7 : Construction of the object-aware placement mask $M_{f}$ for Sheet Metal, Vial, Wallplugs, and Walnuts. Each row shows the MRSP field, its restriction to the object region $\Omega$ , thresholded response, retained largest connected component, and seed-dependent placement regions.

Stage	Time (ms)	Share (%)
OBS foreground extraction	154	26.3
MRSP noise generation	12	2.0
Placement-mask computation	37	6.3
Defect placement	5	0.9
CIELAB color harmonization	139	23.7
Poisson blending	212	36.2

Table 7 : Per-image timing breakdown of FLASH synthesis at 1024

\times

1024 resolution on a single NVIDIA RTX 3090. Stage times are means over fresh, non-cached images; the sub-stage sum (559 ms) is slightly below the measured total (586 ms) because stages overlap and cache.

PaDiM
Category	Real	Perlin	AnoStyler	FLASH (Ours)
Can	71.49	44.60	64.67	68.93
Fabric	73.89	73.17	58.37	73.17
Fruit Jelly	88.27	69.37	87.24	85.71
Rice	81.31	81.08	6.27	81.08
Sheet Metal	89.64	88.24	65.13	88.24

Table 8 : Per-category image-level F1 (%) across all five detectors on MVTec AD 2. The Mean row averages over the eight categories; bold marks the best synthetic source per detector (the Real oracle is excluded).

PaDiM
Category	Real	Perlin	AnoStyler	FLASH (Ours)
Can	0.16	0.05	0.05	0.05
Fabric	3.36	1.44	0.93	1.01
Fruit Jelly	12.41	4.46	5.13	2.96
Rice	6.26	2.03	6.21	1.74
Sheet Metal	11.95	3.70	11.27	9.08

Table 9 : Per-category pixel-level F1 (%) across all five detectors on MVTec AD 2. The Mean row averages over the eight categories; bold marks the best synthetic source per detector (the Real oracle is excluded).

Figure 8 : Visual comparison of synthetic anomaly generation across the eight MVTec AD 2 categories. Each row uses the same normal host image across methods, with columns showing the clean host followed by DRAEM, NSA, GLASS, AnoStyler, and FLASH (ours).

Figure 9 : Per-category synthesis results for Can, Fabric, Fruit Jelly, and Rice. Each row traces a synthesized instance through the host image, object region $\Omega$ , placement mask $M_{f}$ , retrieved defect, ground-truth mask $M_{gt}$ , the alpha and Poisson composites, their zoomed views, and the absolute difference of each composite against the host. Rows correspond to three seeds of the same category.

Figure 10 : Per-category synthesis results for Sheet Metal, Vial, Wallplugs, and Walnuts; columns as in Figure 9 . These categories carry the constrained supports: a thin specular strip, a transparent vial, and two multi-object scenes in which the placement mask selects which instance receives the defect.

Explore similar work

UniScale: Arbitrary-Scale Industrial Anomaly Generation
Aug 8, 2026Shilei Zeng, Linxin Guan, Xurui Li +2Multimodal Industrial Anomaly Detection
School of Electronic Information and Communications, Huazhong University of Science and Technology
Visual Anomaly Synthesis for Model Selection in Data Scarcity
Sep 29, 2026Daniel Pröll, Thomas Kraxner, Tobias Schaefer +1Model Selection
Digital Factory Vorarlberg GmbH, Dornbirn, Austria · University of Salzburg, Salzburg, Austria · illwerke vkw AG, Bregenz, Austria +1
OSAGEN: Object-Aware Mask Priors and Multistage Decoupled Diffusion for Industrial Anomaly Generation
Jul 31, 2026Jinyi Xu, Peng Chen, Yunkang Cao +3Multimodal Industrial Anomaly Detection Synthetic Image Detection
School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University · School of Artificial Intelligence and Robotics, Hunan University · Department of Computer and Information Science, University of Macau +1

Aug 8, 2026, cs.CVJ/K move · Enter open · S save

UniScale: Arbitrary-Scale Industrial Anomaly Generation

Shilei Zeng, Linxin Guan, Xurui Li, Yaohan Tang+1

School of Electronic Information and Communications, Huazhong University of Science and Technology

Multimodal Industrial Anomaly Detection

Open paper AskPDF arXiv

Industrial anomaly inspection faces a major challenge due to the lack of real-world anomaly samples. While generative models are used to create anomaly data, existing methods still struggle when handling small-scale anomalies. This failure occurs because extreme downsampling in diffusion models causes the information of small anomalies to be lost in the latent space. To address this, we introduce UniScale, a unified training and inference framework for high-fidelity industrial anomaly generation across arbitrary scales. During training, we introduce an Error-Suppressed Multi-Scale Training (EMT) strategy, which enables the model to learn the rich location-aware textures of anomalies, while suppressing upsampling-induced interpolation errors in texture acquisition, ensuring the model is capable of learning small-scale anomalies, while remaining effective for regular scale anomalies. For inference, we propose Generation-then-Fusion Denoising. It decouples anomaly generation from background integration, preventing small anomalies from being overwhelmed. Extensive experiments demonstrate that our method outperforms state-of-the-art competitors in both anomaly generation quality and downstream detection performance. It achieves a relative IS(a) improvement of 45.86% (from 1.81 to 2.64) on VisA and 37.70% (from 1.22 to 1.68) on MVTec AD 2, while also improving the downstream pixel-level IoU by 4.22% on VisA and AUROC by 6.55% on MVTec AD 2. Code is available at https://github.com/HUST-SLOW/UniScale.

Abstract

Explore similar work

UniScale: Arbitrary-Scale Industrial Anomaly Generation

Visual Anomaly Synthesis for Model Selection in Data Scarcity

OSAGEN: Object-Aware Mask Priors and Multistage Decoupled Diffusion for Industrial Anomaly Generation