# Ensembled Cold-Diffusion Restorations for Unsupervised Anomaly Detection

arXiv: https://arxiv.org/abs/2407.06635 · HTML: https://mlsanity.com/paper/2407.06635/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 25 references that are in the map.
- First posted on arXiv 9 Jul 2024.

## Builds on (most cited first, 18 of 18)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization](https://mlsanity.com/paper/2011.08785/) (2020)
- [CutPaste: Self-Supervised Learning for Anomaly Detection and Localization](https://mlsanity.com/paper/2104.04015/) (2021)
- [Anomaly Detection via Reverse Distillation from One-Class Embedding](https://mlsanity.com/paper/2201.10703/) (2022)
- [CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows](https://mlsanity.com/paper/2107.12571/) (2021)
- [Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise](https://mlsanity.com/paper/2208.09392/) (2022)
- [Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study](https://mlsanity.com/paper/2004.03271/) (2020)
- [Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization](https://mlsanity.com/paper/2109.15222/) (2021)
- [Fast Unsupervised Brain Anomaly Detection and Segmentation with Diffusion Models](https://mlsanity.com/paper/2206.03461/) (2022)
- [Unsupervised Lesion Detection via Image Restoration with a Normative Prior](https://mlsanity.com/paper/2005.00031/) (2020)
- [Detecting Outliers with Foreign Patch Interpolation](https://mlsanity.com/paper/2011.04197/) (2020)
- [Detecting Outliers with Poisson Image Interpolation](https://mlsanity.com/paper/2107.02622/) (2021)
- [Unsupervised Pathology Detection: A Deep Dive Into the State of the Art](https://mlsanity.com/paper/2303.00609/) (2023)
- [Unsupervised Anomaly Localization with Structural Feature-Autoencoders](https://mlsanity.com/paper/2208.10992/) (2022)
- [Many tasks make light work: Learning to localise medical anomalies from multiple synthetic tasks](https://mlsanity.com/paper/2307.00899/) (2023)
- [DISYRE: Diffusion-Inspired SYnthetic REstoration for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2311.15453/) (2023)
- [Achieving state-of-the-art performance in the Medical Out-of-Distribution (MOOD) challenge using plausible synthetic anomalies](https://mlsanity.com/paper/2308.01412/) (2023)

## Built on by (most cited first, 12 of 12)

- [Are CLIP features all you need for Universal Synthetic Image Origin Attribution?](https://mlsanity.com/paper/2408.09153/) (2024)
- [A Survey on Diffusion Models for Anomaly Detection](https://mlsanity.com/paper/2501.11430/) (2025)
- [MAD-AD: Masked Diffusion for Unsupervised Brain Anomaly Detection](https://mlsanity.com/paper/2502.16943/) (2025)
- [Anomaly Detection and Generation with Diffusion Models: A Survey](https://mlsanity.com/paper/2506.09368/) (2025)
- [Enhancing Reconstruction-Based Out-of-Distribution Detection in Brain MRI with Model and Metric Ensembles](https://mlsanity.com/paper/2412.17586/) (2024)
- [Deep Unsupervised Anomaly Detection in Brain Imaging: Large-Scale Benchmarking and Bias Analysis](https://mlsanity.com/paper/2512.01534/) (2025)
- [A Principled Approach to Unsupervised Anomaly Detection](https://mlsanity.com/paper/2609.21800/) (2026)
- [Out-of-Distribution Detection in Medical Imaging via Diffusion Trajectories](https://mlsanity.com/paper/2507.23411/) (2025)
- [Wasserstein-Aligned Localisation for VLM-Based Distributional OOD Detection in Medical Imaging](https://mlsanity.com/paper/2605.05161/) (2026)
- [Group Equivariant Diffusion for Anomaly Detection in Computational Cytology](https://mlsanity.com/paper/2607.25503/) (2026)
- [Dense Temporal Contrast Synthesis via Conditioned Latent Transport](https://mlsanity.com/paper/2607.29394/) (2026)
- [MIRTO: a registration-gated, multiverse-tested evaluation protocol for unsupervised anomaly segmentation in brain MRI](https://mlsanity.com/paper/2610.02136/) (2026)

## Abstract (arXiv)

Unsupervised Anomaly Detection (UAD) methods aim to identify anomalies in test samples comparing them with a normative distribution learned from a dataset known to be anomaly-free. Approaches based on generative models offer interpretability by generating anomaly-free versions of test images, but are typically unable to identify subtle anomalies. Alternatively, approaches using feature modelling or self-supervised methods, such as the ones relying on synthetically generated anomalies, do not provide out-of-the-box interpretability. In this work, we present a novel method that combines the strengths of both strategies: a generative cold-diffusion pipeline (i.e., a diffusion-like pipeline which uses corruptions not based on noise) that is trained with the objective of turning synthetically-corrupted images back to their normal, original appearance. To support our pipeline we introduce a novel synthetic anomaly generation procedure, called DAG, and a novel anomaly score which ensembles restorations conditioned with different degrees of abnormality. Our method surpasses the prior state-of-the art for unsupervised anomaly detection in three different Brain MRI datasets.