Unsupervised anomaly detection (UAD) has evolved from building specialized single-class models to unified multi-class models, yet existing multi-class models significantly underperform the most advanced one-for-one counterparts. Moreover, the field has fragmented into specialized methods tailored to specific scenarios (multi-class, 3D, few-shot, etc.), creating deployment barriers and highlighting the need for a unified solution. In this paper, we present Dinomaly2, the first unified framework for full-spectrum image UAD, which bridges the performance gap in multi-class models while seamlessly extending across diverse data modalities and task settings. Guided by the "less is more" philosophy, we demonstrate that the orchestration of five simple element achieves superior performance in a standard reconstruction-based framework. This methodological minimalism enables natural extension across diverse tasks without modification, establishing that simplicity is the foundation of true universality. Extensive experiments on 12 UAD benchmarks demonstrate Dinomaly2's full-spectrum superiority across multiple modalities (2D, multi-view, RGB-3D, RGB-IR), task settings (single-class, multi-class, inference-unified multi-class, few-shot) and application domains (industrial, biological, outdoor). For example, our multi-class model achieves unprecedented 99.9% and 99.3% image-level (I-) AUROC on MVTec-AD and VisA respectively. For multi-view and multi-modal inspection, Dinomaly2 demonstrates state-of-the-art performance with minimum adaptations. Moreover, using only 8 normal examples per class, our method surpasses previous full-shot models, achieving 98.7% and 97.4% I-AUROC on MVTec-AD and VisA. The combination of minimalistic design, computational scalability, and universal applicability positions Dinomaly2 as a unified solution for the full spectrum of real-world anomaly detection applications.

翻译：无监督异常检测（UAD）已从构建专用的单类别模型发展到统一的多类别模型，然而现有的多类别模型性能显著落后于最先进的“一对一”对应模型。此外，该领域已分化为针对特定场景（多类别、3D、少样本等）的专门方法，造成了部署障碍，并突显了对统一解决方案的需求。本文提出Dinomaly2，这是首个面向全谱图像无监督异常检测的统一框架，它在弥合多类别模型性能差距的同时，能够无缝扩展到多种数据模态和任务设置。遵循“少即是多”的理念，我们证明了在一个标准的基于重建的框架中，协调五个简单要素即可实现卓越性能。这种方法论上的极简主义使其能够无需修改即可自然地扩展到不同任务，从而确立了简洁性是真正普适性的基础。在12个UAD基准测试上的广泛实验表明，Dinomaly2在多种模态（2D、多视角、RGB-3D、RGB-IR）、任务设置（单类别、多类别、推理统一的多类别、少样本）和应用领域（工业、生物、户外）均展现出全谱系优越性。例如，我们的多类别模型在MVTec-AD和VisA上分别实现了前所未有的99.9%和99.3%的图像级（I-）AUROC。对于多视角和多模态检测，Dinomaly2以最小的适配实现了最先进的性能。此外，仅使用每类别8个正常样本，我们的方法便超越了先前的全样本模型，在MVTec-AD和VisA上分别达到了98.7%和97.4%的I-AUROC。极简的设计、计算的可扩展性以及普适的应用性相结合，使Dinomaly2成为适用于现实世界全谱异常检测应用的统一解决方案。