Training Free Zero-Shot Visual Anomaly Localization via Diffusion Inversion

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hicsonmez, Samet, Shabayek, Abd El Rahman, Aouada, Djamila
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909988575772672
author Hicsonmez, Samet
Shabayek, Abd El Rahman
Aouada, Djamila
author_facet Hicsonmez, Samet
Shabayek, Abd El Rahman
Aouada, Djamila
contents Zero-Shot image Anomaly Detection (ZSAD) aims to detect and localise anomalies without access to any normal training samples of the target data. While recent ZSAD approaches leverage additional modalities such as language to generate fine-grained prompts for localisation, vision-only methods remain limited to image-level classification, lacking spatial precision. In this work, we introduce a simple yet effective training-free vision-only ZSAD framework that circumvents the need for fine-grained prompts by leveraging the inversion of a pretrained Denoising Diffusion Implicit Model (DDIM). Specifically, given an input image and a generic text description (e.g., "an image of an [object class]"), we invert the image to obtain latent representations and initiate the denoising process from a fixed intermediate timestep to reconstruct the image. Since the underlying diffusion model is trained solely on normal data, this process yields a normal-looking reconstruction. The discrepancy between the input image and the reconstructed one highlights potential anomalies. Our method achieves state-of-the-art performance on VISA dataset, demonstrating strong localisation capabilities without auxiliary modalities and facilitating a shift away from prompt dependence for zero-shot anomaly detection research. Code is available at https://github.com/giddyyupp/DIVAD.
format Preprint
id arxiv_https___arxiv_org_abs_2601_08022
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Training Free Zero-Shot Visual Anomaly Localization via Diffusion Inversion
Hicsonmez, Samet
Shabayek, Abd El Rahman
Aouada, Djamila
Computer Vision and Pattern Recognition
Zero-Shot image Anomaly Detection (ZSAD) aims to detect and localise anomalies without access to any normal training samples of the target data. While recent ZSAD approaches leverage additional modalities such as language to generate fine-grained prompts for localisation, vision-only methods remain limited to image-level classification, lacking spatial precision. In this work, we introduce a simple yet effective training-free vision-only ZSAD framework that circumvents the need for fine-grained prompts by leveraging the inversion of a pretrained Denoising Diffusion Implicit Model (DDIM). Specifically, given an input image and a generic text description (e.g., "an image of an [object class]"), we invert the image to obtain latent representations and initiate the denoising process from a fixed intermediate timestep to reconstruct the image. Since the underlying diffusion model is trained solely on normal data, this process yields a normal-looking reconstruction. The discrepancy between the input image and the reconstructed one highlights potential anomalies. Our method achieves state-of-the-art performance on VISA dataset, demonstrating strong localisation capabilities without auxiliary modalities and facilitating a shift away from prompt dependence for zero-shot anomaly detection research. Code is available at https://github.com/giddyyupp/DIVAD.
title Training Free Zero-Shot Visual Anomaly Localization via Diffusion Inversion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.08022