---
title: '3D-ADAM: Industrial 3D Anomaly Benchmark'
url: https://www.emergentmind.com/topics/3d-adam
type: topic
---

# 3D-ADAM: Industrial 3D Anomaly Benchmark

Searching arXiv for recent papers on 3D-ADAM and closely related 3D anomaly detection benchmarks/methods.
3D-ADAM, short for **3D Anomaly Detection in Advanced Manufacturing**, is a **large-scale, real-world, multi-sensor RGB+3D industrial anomaly detection dataset** introduced to support **high-precision anomaly detection and localization** under conditions closer to industrial deployment than earlier benchmarks. It was designed to address limitations attributed to prior 3D anomaly datasets, especially limited defect diversity, limited machine-element coverage, overly controlled capture conditions, and insufficient realism for advanced manufacturing environments. The dataset combines **real manufactured parts**, **real defect instances**, **multiple industrial depth sensors**, **multi-view capture in a working robotics cell**, and **machine-element-level annotations** in addition to defect labels [2507.07838].

## 1. Concept and intended scope

3D-ADAM is positioned as a benchmark for **3D anomaly detection**, **RGB+3D anomaly detection**, and **localization** in manufacturing settings where part pose, lighting, and visibility are not tightly controlled. Its stated objective is to be more representative of real industrial deployment, particularly for inspection scenarios in which parts are observed from multiple views with varying orientations, ambient illumination, and partial occlusions [2507.07838].

A central feature of the dataset is its explicit treatment of **machine elements** as annotation targets alongside defects. The paper identifies this as a key distinction from prior datasets because feature-level distinctions such as **faces, edges, fillets, chamfers, holes, gears,** and related structures matter in manufacturing inspection but are absent from earlier benchmarks. This suggests a shift from purely object-level anomaly detection toward **feature-aware localization and classification**, although the benchmark reported in the paper is framed around anomaly detection and localization rather than a full machine-element recognition task [2507.07838].

The dataset is also explicitly industrial in provenance. Unlike synthetic or heavily curated benchmarks, 3D-ADAM uses **actual manufactured parts and actual physical defects**, and it was captured **in a real industrial environment** rather than a highly controlled laboratory setting. The paper’s broader claim is that this realism exposes substantial weaknesses in models that perform strongly on simpler benchmarks [2507.07838].

## 2. Position within the 3D anomaly-detection literature

The paper situates 3D-ADAM against three reference datasets: **MVTec 3D-AD**, **Eyecandies**, and **Real3D-AD** [2507.07838]. Among these, **MVTec 3D-AD** is described as the most widely used benchmark for unsupervised 3D anomaly detection and localization, comprising **4147 scans** from **10 real-world object categories**, with anomaly-free train/validation sets and a mixed test set containing **948 anomalous test images** and **249 anomaly-free test images** [2112.09045]. That benchmark established the basic industrial-inspection setting in which a method is trained only on normal data and must produce both sample-level anomaly decisions and pixel-/point-level localization, but its capture conditions are comparatively controlled and its ontology is narrower [2112.09045].

Relative to **MVTec 3D-AD**, 3D-ADAM is described as more varied in **defect classes**, **machine-element annotations**, **part categories**, and **capture conditions**, and as being collected **in-the-wild** rather than in a controlled setup [2507.07838]. Relative to **Real3D-AD**, the paper states that 3D-ADAM goes further in **industrial realism** and in the breadth of annotated defect and feature types, while including **RGB + XYZ alignment from multiple sensors** [2507.07838]. Relative to **Eyecandies**, it emphasizes that Eyecandies uses synthetic parts and defects, whereas 3D-ADAM uses real manufactured parts and physical defects [2507.07838].

This positioning places 3D-ADAM within a broader transition in the field. Recent methods such as **MC3D-AD** target **multi-category 3D anomaly detection** with unified geometry-aware reconstruction [2505.01969], **DAS3D** targets **dual-modality RGB+depth anomaly detection** with anomaly synthesis [2410.09821], and **CoGeoAD** targets **zero-shot 3D anomaly detection** through hierarchical color-geometric fusion [2606.25273]. The introduction of 3D-ADAM suggests that progress on such methods increasingly depends on datasets that better reflect real deployment conditions rather than benchmark regularities.

## 3. Dataset composition, ontology, and reported statistics

The paper reports the overall scale of 3D-ADAM in several places, and some of those figures differ across sections. The abstract reports **14,120 high-resolution scans**, **217 unique parts**, **4 industrial depth sensors**, **27,346 annotated defect instances** from **12 categories**, and **8,110 annotations of machine element features**, spanning relevant mechanical design form factors [2507.07838]. The dataset section and table are described as giving **12,192 scans distributed across four sensors**, while the breakdown table totals **14,120 images** across the categories; the paper’s headline figure is therefore the larger **14,120** count [2507.07838].

A similar discrepancy is reported for category counts and machine-element annotations. The abstract says **28 categories**, whereas the dataset section/table enumerates **29 distinct object categories** [2507.07838]. Likewise, the abstract reports **8,110 machine-element annotations**, while the dataset section/table reports **27,346 machine-element annotations** in parallel with **27,346 defect annotations**, suggesting a one-to-one propagation of annotations per defect instance [2507.07838]. These differences are part of the published description and are not resolved in the provided text.

The dataset includes **12 defect classes**:

| Type | Classes |
|---|---|
| Defect classes | cuts, bulges, holes, gaps, burrs, cracks, scratches, marks, warping, roughness, over-extrusion, under-extrusion |

It also includes **16 machine element classes** spanning:

| Type | Classes |
|---|---|
| Machine element classes | faces, edges, internal/external fillets, internal/external chamfers, holes, kerfs, tapers, indents, counterbores, countersinks, spur gear teeth, rack gear teeth, spiral gear teeth, clockwise helical gear teeth, counter-clockwise helical gear teeth |

The parts are described as forming a **robot arm mechanism**, based on the open-source **BCN3D-Moveo** system and augmented with additional parts from **Thingi10K** so that the full set of machine elements is represented [2507.07838]. Listed examples include base, shoulder, forearm, elbow, wrist, gripper, and multiple gear subcomponents. The total table reports **217 parts**, **14,120 images**, **27,346 defect annotations**, and **27,346 machine element annotations** [2507.07838].

## 4. Acquisition environment and data representation

3D-ADAM was captured in a **real industrial robotics applications development cell at HAL Robotics** [2507.07838]. The acquisition setup used four industrial 3D sensors:

| Sensor |
|---|
| MechMind LSR-L |
| MechMind Nano |
| Intel RealSense D455 |
| Stereolabs Zed 2i |

The mounting geometry was heterogeneous. An **ABB IRB 120 robot arm** positioned the **MechMind Nano**, **RealSense**, and **Zed 2i**, while the **MechMind LSR-L** was mounted above the cell [2507.07838]. A part fixture allowed **360° rotation** around the primary axis and **90° motion** around a secondary axis. The view-acquisition protocol involved at least one full rotation of the primary axis, with scans every **45 degrees**, and the secondary axis fixed at **0° and 30°**, with additional orientations used when required for coverage [2507.07838].

Lighting was intentionally variable. Scanning occurred under **indirect natural light**, **diffuse artificial light when needed**, different times of day, and weather and seasonal variation [2507.07838]. The paper presents this variability as a core design principle rather than a nuisance, since the goal is to approximate industrial deployment rather than laboratory repeatability.

For each scan, the dataset contains **RGB images** and **XYZ point cloud data**, stored as **PNG RGB images** and **.PLY** point clouds with a **1-to-1 pixel correspondence** between RGB and XYZ data [2507.07838]. The sensors are described as capturing six-channel images containing `r, g, b, x, y, z` [2507.07838]. This representation places 3D-ADAM squarely in the multimodal RGB+3D regime now used by methods such as DAS3D and CoGeoAD, which explicitly rely on aligned appearance and geometry channels [2410.09821].

## 5. Manufacturing process, defect creation, and annotation protocol

The parts were manufactured by **Fused Deposition Modelling (FDM)** in **PLA** using **two Prusa i3**, **one Ender 3 Pro**, and **one Ultimaker 2** [2507.07838]. Defects originated from two sources. Some defects occurred naturally during printing, with the paper noting that even some nominally “good” parts exhibited minor defects discovered during annotation; **burrs** and **roughness** often arose this way [2507.07838]. Other defects were deliberately induced either by changing print parameters or by manual intervention. Process-induced defects included **bulges**, **gaps**, **warping**, **over-extrusion**, and **under-extrusion**, while handling- or manipulation-induced defects included **cuts**, **holes**, **cracks**, **marks**, and **scratches** [2507.07838].

The annotation pipeline is one of the dataset’s principal technical contributions. For each part instance, the dataset provides a **part segmentation mask**, a **defect segmentation mask**, and **machine element bounding boxes with class labels** [2507.07838]. Foreground part masks were produced semi-automatically using **Cutie** and then manually checked and corrected. Defect and machine-element annotations were performed manually on **MechMind Nano** images because they provide the highest defect detail. A **single expert annotator** labeled all Nano images, and **HAL Robotics experts** provided verification and feedback [2507.07838].

Annotations were then propagated across sensors: **homographic transforms** were used to project Nano annotations onto images from the other sensors, after which the propagated labels were manually checked and corrected where needed [2507.07838]. This procedure is notable because it aims to preserve label consistency across a multi-sensor RGB+3D benchmark while maintaining alignment between appearance and geometry. A plausible implication is that 3D-ADAM is intended not only for per-sensor evaluation but also for research on cross-sensor robustness.

## 6. Benchmark tasks, evaluation protocol, and empirical difficulty

The benchmark is reported in a **supervised** setting for **3D anomaly detection**, **RGB+3D anomaly detection**, and **localization** [2507.07838]. The split uses an **anomaly-free training set** containing all defect-free scans, while the defective scans are divided into **validation** and **test** with a **60:40 split** between test and validation [2507.07838]. The evaluated models are **TransFusion**, **CPMF**, **3DSR**, and **Shape-Guided**, all of which are identified as methods known from **MVTec 3D-AD** benchmarks [2507.07838].

The reported metrics are standard: **AUROC** for image-level anomaly detection and **AUPRO** for pixel-level anomaly localization [2507.07838]. This aligns 3D-ADAM with prevailing 3D-AD evaluation practice. For comparison, **MVTec 3D-AD** evaluates sample-level classification with **AUROC** and localization with **AU-PRO@0.3**, emphasizing that high false-positive rates can make segmentation practically meaningless when anomalies are small [2112.09045]. 3D-ADAM’s use of AUROC and AUPRO preserves that industrial anomaly-detection framing.

The paper’s principal empirical conclusion is qualitative but unambiguous: **all state-of-the-art models perform significantly worse on 3D-ADAM than on MVTec 3D-AD** [2507.07838]. The results table is said to appear in supplementary material rather than the main text, but the authors attribute the performance drop to the dataset’s broader defect ontology, increased geometry diversity, machine-element variation, sensor differences, variable lighting, pose changes, and partial occlusion [2507.07838].

This claim is consistent with broader trends in later 3D-AD research. For example, **CoGeoAD** reports strong zero-shot performance on MVTec3D-AD and Eyecandies but also treats cross-dataset transfer as a central challenge [2606.25273]. Likewise, **IEC3D-AD** was introduced on the grounds that prior benchmarks do not capture the subtle defects and dense full-coverage point clouds required for industrial equipment inspection [2511.03267]. Taken together, these developments suggest that benchmark difficulty is increasingly driven by realism rather than by the formal anomaly-detection task definition alone.

## 7. Industrial relevance, limitations, and research implications

The paper includes an external validation of annotation quality through an expert survey involving **five industry experts** from **three manufacturing organizations** spanning industrial R&D, digital process manufacturing, and robotics [2507.07838]. Each expert labeled a random subset of defective scans equal to about **1% of the total dataset**, receiving instructions and defect-free examples of the same parts but no annotated examples from the dataset itself, approximating a blind evaluation [2507.07838]. Because the survey labels were 2D-based, the comparison used **IoU** and **PRO**. The reported results were **mean IoU = 0.6**, **standard deviation = 0.04**, **mean PRO = 0.76**, and **standard deviation = 0.058** [2507.07838]. The paper interprets this as strong agreement between expert labels and dataset ground truth, with experts tending toward slightly more false positives than false negatives.

The paper is also explicit about limitations. All parts are printed in **PLA**, limiting material diversity and surface-appearance variation. The dataset does not contain all possible industrial defect types. It does not provide complete closed 3D scans from all viewpoints, unlike some prior datasets; however, the authors argue that this is more realistic for industrial deployment, where full-view scans are often unavailable. The effect of changing material properties on defect visibility is not studied [2507.07838].

These limitations shape the dataset’s likely role in the literature. The paper argues that future methods will need to handle **multi-view, multi-sensor, real-world noise**, and that anomaly detection should become **feature-aware**, not only object-aware [2507.07838]. It also suggests relevance to **few-shot**, **zero-shot**, and **machine-element-aware localization and classification**. This suggests that 3D-ADAM is not merely a larger benchmark, but part of a broader move toward deployment-oriented evaluation in 3D industrial inspection.

A common misconception would be to treat 3D-ADAM as simply a scaled-up version of earlier RGB+3D datasets. The published description indicates a more specific claim: the dataset’s novelty lies not only in scale, but in the combination of **real industrial capture**, **multi-sensor aligned RGB+XYZ data**, **broad defect ontology**, and **machine-element annotations** [2507.07838]. Another possible misconception would be to assume that the dataset is internally uniform in all reported counts; the paper itself reports differing totals for scans, category counts, and machine-element annotations across sections, and those differences should be preserved when citing the benchmark rather than silently normalized [2507.07838].

Source: https://www.emergentmind.com/topics/3d-adam