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

Alex Costanzino1, Pierluigi Zama Ramirez1, Luigi Lella1, Matteo Ragaglia2, Alessandro Oliva2, Giuseppe Lisanti1, Luigi Di Stefano1
1University of Bologna, 2SACMI Imola
Accepted at ICCV 2025
Paper [TBD] arXiv Video [TBD] Code [TBD] Data [TBD]
Teaser image

Thanks to a high-end acquisition setup and with a thorough processing pipeline we are able to generate data for Multimodal and Multiview 3D Anomaly Detection.

Abstract

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.

Teaser image

We adapted state-of-the-art singleview methods and assessed their performance on SiM3D.

BibTeX

@inproceedings{costanzino2025sim3d,
  author    = {Costanzino, Alex and Zama Ramirez, Pierluigi and Lella, Luigi and Ragaglia, Matteo and Oliva, Alessandro and Lisanti, Giuseppe and Di Stefano, Luigi},
  title     = {SiM3D: Single-instance Multiview Multimodal and Multisetup 3D Anomaly Detection Benchmark},
  booktitle = {International Conference on Computer Vision (ICCV)},
  year      = {2025},
}