SiM3D: Single-instance Multiview Multimodal and Multisetup 3D Anomaly Detection Benchmark

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Costanzino, Alex, Ramirez, Pierluigi Zama, Lella, Luigi, Ragaglia, Matteo, Oliva, Alessandro, Lisanti, Giuseppe, Di Stefano, Luigi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913970965708800
author Costanzino, Alex
Ramirez, Pierluigi Zama
Lella, Luigi
Ragaglia, Matteo
Oliva, Alessandro
Lisanti, Giuseppe
Di Stefano, Luigi
author_facet Costanzino, Alex
Ramirez, Pierluigi Zama
Lella, Luigi
Ragaglia, Matteo
Oliva, Alessandro
Lisanti, Giuseppe
Di Stefano, Luigi
contents We propose SiM3D, the first benchmark considering the integration of multiview and multimodal information for comprehensive 3D anomaly detection and segmentation (ADS), where the task is to produce a voxel-based Anomaly Volume. Moreover, SiM3D focuses on a scenario of high interest in manufacturing: single-instance anomaly detection, where only one object, either real or synthetic, is available for training. In this respect, SiM3D stands out as the first ADS benchmark that addresses the challenge of generalising from synthetic training data to real test data. SiM3D includes a novel multimodal multiview dataset acquired using top-tier industrial sensors and robots. The dataset features multiview high-resolution images (12 Mpx) and point clouds (7M points) for 333 instances of eight types of objects, alongside a CAD model for each type. We also provide manually annotated 3D segmentation GTs for anomalous test samples. To establish reference baselines for the proposed multiview 3D ADS task, we adapt prominent singleview methods and assess their performance using novel metrics that operate on Anomaly Volumes.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21549
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SiM3D: Single-instance Multiview Multimodal and Multisetup 3D Anomaly Detection Benchmark
Costanzino, Alex
Ramirez, Pierluigi Zama
Lella, Luigi
Ragaglia, Matteo
Oliva, Alessandro
Lisanti, Giuseppe
Di Stefano, Luigi
Computer Vision and Pattern Recognition
We propose SiM3D, the first benchmark considering the integration of multiview and multimodal information for comprehensive 3D anomaly detection and segmentation (ADS), where the task is to produce a voxel-based Anomaly Volume. Moreover, SiM3D focuses on a scenario of high interest in manufacturing: single-instance anomaly detection, where only one object, either real or synthetic, is available for training. In this respect, SiM3D stands out as the first ADS benchmark that addresses the challenge of generalising from synthetic training data to real test data. SiM3D includes a novel multimodal multiview dataset acquired using top-tier industrial sensors and robots. The dataset features multiview high-resolution images (12 Mpx) and point clouds (7M points) for 333 instances of eight types of objects, alongside a CAD model for each type. We also provide manually annotated 3D segmentation GTs for anomalous test samples. To establish reference baselines for the proposed multiview 3D ADS task, we adapt prominent singleview methods and assess their performance using novel metrics that operate on Anomaly Volumes.
title SiM3D: Single-instance Multiview Multimodal and Multisetup 3D Anomaly Detection Benchmark
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.21549