Multimodal Industrial Anomaly Detection via Geometric Prior

• URL: http://arxiv.org/abs/2603.22757v1
• Date: Tue, 24 Mar 2026 03:34:08 GMT
• Title: Multimodal Industrial Anomaly Detection via Geometric Prior
• Abstract summary: We propose a novel Geometric Prior-based Anomaly Detection network (GPAD)<n>Our model outperforms the State-of-the-art (SOTA) methods in detection accuracy on both MVTec-3D AD and Eyecandies datasets.
• Score: 15.518007234069358
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The purpose of multimodal industrial anomaly detection is to detect complex geometric shape defects such as subtle surface deformations and irregular contours that are difficult to detect in 2D-based methods. However, current multimodal industrial anomaly detection lacks the effective use of crucial geometric information like surface normal vectors and 3D shape topology, resulting in low detection accuracy. In this paper, we propose a novel Geometric Prior-based Anomaly Detection network (GPAD). Firstly, we propose a point cloud expert model to perform fine-grained geometric feature extraction, employing differential normal vector computation to enhance the geometric details of the extracted features and generate geometric prior. Secondly, we propose a two-stage fusion strategy to efficiently leverage the complementarity of multimodal data as well as the geometric prior inherent in 3D points. We further propose attention fusion and anomaly regions segmentation based on geometric prior, which enhance the model's ability to perceive geometric defects. Extensive experiments show that our multimodal industrial anomaly detection model outperforms the State-of-the-art (SOTA) methods in detection accuracy on both MVTec-3D AD and Eyecandies datasets.

Related papers

• Real-IAD MVN: A Multi-View Normal Vector Dataset and Benchmark for High-Fidelity Industrial Anomaly Detection [13.79855998324516]
  We introduce Real-IAD-MVN (Multi-View Normal), a large-scale industrial dataset.<n>By upgrading our acquisition system, Real-IAD-MVN captures high-fidelity surface normal maps from five distinct viewpoints.<n>This provides a comprehensive geometric representation at a micro-detail level, making previously invisible side-wall and occluded defects explicitly detectable.
  arXiv  Detail & Related papers  (2026-05-08T02:34:51Z)
• Text-Guided Multimodal Unified Industrial Anomaly Detection [71.95719669933312]
  We propose a unified multimodal industrial anomaly detection framework guided by text semantics.<n>The framework consists of two core modules: a Geometry-Aware Cross-Modal Mapper and an Object-Conditioned Textual Feature Adaptor.<n>Our method achieves state-of-the-art performance in classification and localization under unsupervised settings.
  arXiv  Detail & Related papers  (2026-04-24T13:21:22Z)
• A 3DGS-Diffusion Self-Supervised Framework for Normal Estimation from a Single Image [5.588610465556571]
  The lack of spatial dimensional information remains a challenge in normal estimation from a single image.<n>Recent diffusion-based methods have demonstrated significant potential in 2D-to-3D implicit mapping.<n>This paper proposes SINGAD, a novel Self-supervised framework from a single Image for Normal estimation.
  arXiv  Detail & Related papers  (2025-08-08T02:32:33Z)
• Geometry Distributions [51.4061133324376]
  We propose a novel geometric data representation that models geometry as distributions. Our approach uses diffusion models with a novel network architecture to learn surface point distributions. We evaluate our representation qualitatively and quantitatively across various object types, demonstrating its effectiveness in achieving high geometric fidelity.
  arXiv  Detail & Related papers  (2024-11-25T04:06:48Z)
• MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors [24.753860375872215]
  This paper presents a Transformer-based monocular 3D object detection method called MonoDGP.<n>It adopts perspective-invariant geometry errors to modify the projection formula.<n>Our method demonstrates state-of-the-art performance on the KITTI benchmark without extra data.
  arXiv  Detail & Related papers  (2024-10-25T14:31:43Z)
• Towards Unified 3D Object Detection via Algorithm and Data Unification [70.27631528933482]
  We build the first unified multi-modal 3D object detection benchmark MM- Omni3D and extend the aforementioned monocular detector to its multi-modal version. We name the designed monocular and multi-modal detectors as UniMODE and MM-UniMODE, respectively.
  arXiv  Detail & Related papers  (2024-02-28T18:59:31Z)
• Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection [59.41026558455904]
  We focus on multi-modal anomaly detection. Specifically, we investigate early multi-modal approaches that attempted to utilize models pre-trained on large-scale visual datasets. We propose a Local-to-global Self-supervised Feature Adaptation (LSFA) method to finetune the adaptors and learn task-oriented representation toward anomaly detection.
  arXiv  Detail & Related papers  (2024-01-06T07:30:41Z)
• SeMAnD: Self-Supervised Anomaly Detection in Multimodal Geospatial Datasets [0.0]
  SeMAnD is able to detect real-world defects and outperforms domain-agnostic anomaly detection strategies by 4.8-19.7%. We show that model performance increases (i) up to 20.4% as the number of input modalities increase and (ii) up to 22.9% as the diversity and strength of training data augmentations increase.
  arXiv  Detail & Related papers  (2023-09-26T20:18:31Z)
• Multimodal Industrial Anomaly Detection via Hybrid Fusion [59.16333340582885]
  We propose a novel multimodal anomaly detection method with hybrid fusion scheme. Our model outperforms the state-of-the-art (SOTA) methods on both detection and segmentation precision on MVTecD-3 AD dataset.
  arXiv  Detail & Related papers  (2023-03-01T15:48:27Z)
• Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection [70.71934539556916]
  We learn geometry-guided depth estimation with projective modeling to advance monocular 3D object detection. Specifically, a principled geometry formula with projective modeling of 2D and 3D depth predictions in the monocular 3D object detection network is devised. Our method remarkably improves the detection performance of the state-of-the-art monocular-based method without extra data by 2.80% on the moderate test setting.
  arXiv  Detail & Related papers  (2021-07-29T12:30:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.