---
title: 'RealIAD-HD: High-Res Industrial Anomaly Benchmark'
url: https://www.emergentmind.com/topics/realiad-hd
type: topic
---

# RealIAD-HD: High-Res Industrial Anomaly Benchmark

RealIAD-HD denotes a high-resolution industrial anomaly detection benchmark derived from Real-IAD, the large-scale real-world multi-view industrial anomaly detection dataset. In the high-resolution anomaly detection literature, the concrete experimental instantiation is RealIAD-2K: a standardized top-view subset comprising Bottle Cap, Mint, and USB Adaptor, with all images resized to \(2048\times 2048\) [2508.12931]. The term is not introduced as a named variant in the original Real-IAD paper, where high resolution is an inherent property of Real-IAD itself rather than a separately defined release [2403.12580].

## 1. Definition and nomenclature

The term has two distinct usages in the published material considered here.

| Usage | Source | Meaning |
|---|---|---|
| RealIAD-HD | HiAD benchmark paper | Curated high-resolution benchmark derived from Real-IAD; experimentally instantiated as RealIAD-2K |
| “RealIAD-HD” | Real-IAD-MVN explanatory material | Informal label for the high-precision, multi-view pseudo-3D variant Real-IAD-MVN |

In the original Real-IAD paper, there is no dataset variant formally named “RealIAD-HD.” Real-IAD is introduced instead as a **large-scale, real-world, multi-view, high-resolution industrial anomaly detection dataset**, with released image resolutions in the **2000–5000** range and native camera resolution \(3648\times 5472\) [2403.12580]. The later HiAD paper explicitly curates a high-resolution benchmark from that source dataset, and calls this benchmark **RealIAD-HD**; the concrete processed dataset used in experiments is **RealIAD-2K** [2508.12931].

A separate later usage appears in the Real-IAD-MVN line. There, the explanatory text states that if someone refers to “RealIAD-HD,” they are essentially pointing at the **high-precision, multi-view pseudo-3D variant** of Real-IAD, namely Real-IAD-MVN [2605.07149]. This suggests that the label is context-dependent: in one context it denotes a 2D high-resolution benchmark configuration, and in another it functions as shorthand for a high-fidelity geometric extension.

## 2. Source dataset: Real-IAD

RealIAD-HD is derived from Real-IAD, which was proposed to address the saturation and limited scale of earlier industrial anomaly detection datasets. Real-IAD contains **151,050** images of **30 distinct industrial products**, with **99,721** normal images and **51,329** anomalous images, and uses a **5 views per sample** acquisition protocol consisting of **one top view + four side views at 45°** [2403.12580]. The dataset covers **metal, plastic, wood, ceramics, and mixed materials**, and includes both simple parts and more complex assemblies.

Real-IAD also formalizes a broader anomaly taxonomy and evaluation regime than earlier single-view RGB datasets. The paper lists **8 canonical defect types**—**Pit**, **Deformation**, **Abrasion**, **Scratch**, **Damage**, **Missing part**, **Foreign object**, and **Contamination**—and introduces both conventional unsupervised industrial anomaly detection and **Fully Unsupervised Industrial Anomaly Detection (FUIAD)** [2403.12580]. It includes **image-level** labels, **pixel-level** masks, and **sample-level** grouping across the five views.

The high-resolution character of Real-IAD is foundational for RealIAD-HD. The paper states that the dataset deliberately increases resolution to capture more subtle defect features, with released images in the **2–5K pixel** range after cropping from original captures. This is the direct substrate from which the later high-resolution benchmark configuration is constructed [2403.12580].

## 3. Construction and data characteristics of RealIAD-HD

RealIAD-HD is constructed by selecting **three representative product categories** from Real-IAD: **Bottle Cap**, **Mint**, and **USB Adaptor**. These categories are chosen because they have the **smallest average defect areas** in the original Real-IAD dataset and are **very challenging at lower resolutions** [2508.12931]. To standardize the benchmark, the construction uses **only top-view images** and **uniformly resizes all images to \(2048\times 2048\)**. The resulting processed subset is denoted **RealIAD-2K**.

| Category | Split counts | Total |
|---|---|---|
| Bottle Cap | 370 train; 299 test normal; 81 test anomaly | 750 |
| Mint | 306 train; 99 test normal; 322 test anomaly | 727 |
| USB Adaptor | 362 train; 80 test normal; 102 test anomaly | 544 |
| Total | 1038 train; 478 test normal; 505 test anomaly | 2021 |

The protocol follows standard **unsupervised anomaly detection**: training uses only **normal images**, while testing includes both **normal** and **anomalous** images. The anomalies are **real defects** from the manufacturing process rather than synthetic perturbations [2508.12931]. RealIAD-HD reuses the **pixel-level ground-truth masks** from Real-IAD, so evaluation is defined at both image and dense segmentation levels.

The benchmark is explicitly centered on **subtle anomalies**. The paper states that RealIAD-HD has the **smallest relative defect area** among the compared high-resolution benchmarks, and that in several examples the relative defect area is **less than \(0.01\%\)** [2508.12931]. This makes the dataset particularly sensitive to the loss of fine-grained discriminative information under conventional downsampling. A plausible implication is that RealIAD-HD is less a generic high-resolution benchmark than a stress test for methods whose success depends on preserving weak, localized anomaly cues.

## 4. Evaluation protocol and empirical profile

In the HiAD experiments, RealIAD-HD is evaluated with **image-level AUROC (I-AUC)**, **pixel-level AUROC (P-AUC)**, **pixel-level Average Precision (P-AP)**, **pixel-level F1 (P-F1)**, and **Per-Region Overlap (PRO)** [2508.12931]. The image-level anomaly score is defined as the maximum value over the anomaly map \(\mathcal{S}\),
\[
s(X) = \max_{a,b} \mathcal{S}(a,b),
\]
and pixel-level metrics are computed from \(\mathcal{S}(a,b)\) against dense binary ground truth.

Because RealIAD-HD images are \(2\text{K}\), the anomaly map and binary mask are **downsampled to \(512\times 512\)** for metric computation. The paper reports that for **2K images**, this introduces **<0.1% absolute error on all P-metrics** [2508.12931]. The reported evaluation is therefore computationally tractable while remaining close to full-resolution scoring.

Overall results on RealIAD-2K show very high pixel-level separability but substantial variation in segmentation quality across detectors. With HiAD, the reported overall values are: **PatchCore** with **I-AUC 98.37**, **P-AUC 99.89**, **P-AP 45.16**, **P-F1 47.34**, **PRO 99.10**; **ViTAD** with **94.08**, **99.79**, **36.59**, **41.83**, **98.02**; **DeSTSeg** with **93.50**, **99.46**, **54.67**, **53.96**, **95.55**; **RealNet** with **93.02**, **99.63**, **46.84**, **48.86**, **92.71**; **FastFlow** with **93.66**, **99.32**, **25.97**, **32.82**, **96.79**; **RD++** with **88.03**, **98.87**, **29.03**, **36.27**, **94.02**; and **PaDiM** with **89.67**, **99.60**, **20.74**, **28.22**, **97.98** [2508.12931].

The category-wise results indicate different difficulty regimes. **Bottle Cap** is described as comparatively easier, with extremely high **P-AUC** and **PRO**; **Mint** is more challenging, with lower **I-AUC** and **P-AP**; **USB Adaptor** combines complex structure with strong overall detectability under HiAD [2508.12931]. This distribution suggests that RealIAD-HD tests both fine-grained localization and robustness to category-dependent appearance variation.

## 5. Methodological role in high-resolution anomaly detection

RealIAD-HD functions as a benchmark for methods that must preserve subtle anomalies at native or near-native resolution. In the HiAD framework, the central argument is that conventional low-resolution preprocessing can erase the discriminative evidence required for these defects. The paper makes this explicit through PatchCore comparisons on RealIAD-2K: **without HiAD**, at **\(512\times 512\)**, PatchCore reports **I-AUC 91.44**, **P-AUC 99.51**, **P-AP 25.53**, **P-F1 33.43**, **PRO 95.09**; at **\(256\times 256\)**, it reports **84.58**, **97.71**, **10.10**, **18.22**, **83.98**; **with HiAD at 2K**, the same detector reaches **98.37**, **99.89**, **45.16**, **47.34**, **99.10** [2508.12931]. The concrete implication is that RealIAD-HD is not merely a larger-input benchmark: it measures the extent to which a method can avoid the failure mode induced by downsampling.

HiAD addresses the benchmark with a **dual-branch architecture**. The **high-resolution branch** tiles the input image \(X\in\mathbb{R}^{H\times W\times 3}\) into patches and processes them through a detector pool, yielding
\[
\mathcal{S}_\mathcal{H} = G\big(\{ D(f_{i,j}) \mid D=\Phi_{\mathcal{D}(f_{i,j})},\ f_{i,j}\in\mathcal{F} \}\big).
\]
The **low-resolution branch** downsamples the image,
\[
X_\mathcal{L} = Down(X, s)\in\mathbb{R}^{H_\mathcal{L}\times W_\mathcal{L}\times 3},
\]
applies a backbone and detector, and upsamples the resulting anomaly map,
\[
\mathcal{S}_\mathcal{L} = Up(D_\mathcal{L}(\phi(X_\mathcal{L}))).
\]
The final anomaly map is fused by a pixelwise maximum,
\[
\mathcal{S}(a,b) = \max\big(\mathcal{S}_\mathcal{H}(a,b),\ \mathcal{S}_\mathcal{L}(a,b)\big).
\]

The framework further introduces **multi-resolution feature fusion**,
\[
X^k = Down(X, 2^k),\quad \bar{x}_l = \sum_{k=0}^K Up(x_l^k,2^k) w_k,\quad \sum_k w_k=1,
\]
followed by patch features
\[
f_{i,j} = \{\bar{x}_1(i,j),\dots,\bar{x}_L(i,j)\}.
\]
For RealIAD-2K, the paper uses **downsampling rates \(\{0,1\}\)**, **equal weights** by default, **\(M=4\)** detectors, and typically **\(512\times 512\)** high-resolution patches for CNN backbones with stride equal to patch size [2508.12931]. Most methods use **Spatial Clustering Assignment (SCA)** on RealIAD-HD, while **Retrieval Assignment (RA)** is used in the **multi-class** setting. The benchmark therefore serves simultaneously as a dataset and as a methodological proving ground for patch-based, multi-resolution, detector-assigned inference under constrained compute.

## 6. Relation to Real-IAD-MVN and the broader “high-fidelity” line

A later development in the Real-IAD family complicates the interpretation of the label “RealIAD-HD.” Real-IAD-MVN is introduced as a **high-fidelity geometric extension** of the earlier Real-IAD D³ dataset. It replaces sparse 3D point clouds with **Multi-View RGB (MV-RGB) + multi-view surface normal maps (MV-NV)**, using **five viewpoints** and upgrading geometric resolution to around **0.002 mm normal precision** [2605.07149]. It keeps the same **20 categories**, **69 defect types**, and **8,450 samples** as Real-IAD D³, but increases the data volume per sample by **5×** because each sample is captured from five views.

The Real-IAD-MVN material explicitly states that, in the sense in which people often say “HD” or “high-fidelity,” Real-IAD-MVN is exactly that, and that if someone refers to “RealIAD-HD,” they are essentially pointing at this **high-precision, multi-view pseudo-3D variant** of Real-IAD [2605.07149]. This usage differs materially from the HiAD benchmark usage. In the former, “HD” refers to **high-resolution 2D imagery** standardized as RealIAD-2K; in the latter, it refers to **high-fidelity geometric sensing** via dense multi-view photometric-stereo normals.

This suggests that the term “RealIAD-HD” should be interpreted contextually. In high-resolution anomaly detection, it designates a **benchmark configuration** derived from Real-IAD and centered on three top-view 2K categories. In the high-fidelity geometric branch of the Real-IAD line, it serves as an informal descriptor for Real-IAD-MVN’s dense, multi-view pseudo-3D representation. The common thread is not a single canonical dataset name, but an emphasis on preserving information that is lost in lower-fidelity pipelines: either fine image detail in RealIAD-2K or dense micro-geometry in Real-IAD-MVN.

Source: https://www.emergentmind.com/topics/realiad-hd