A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detection

• URL: http://arxiv.org/abs/2603.25159v1
• Date: Thu, 26 Mar 2026 08:26:46 GMT
• Title: A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detection
• Abstract summary: 3D anomaly detection targets the detection and localization of defects in 3D point clouds trained solely on normal data.<n>We propose the Semantically Disentangled Unified Model for 3D Anomaly Detection, which reconstructs features conditioned on disentangled semantic representations.<n>Our method achieves state-of-the-art for both unified and category-specific models, improving object-level AUROC by 2.8% and 9.1%, respectively.
• Score: 3.991584682799934
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 3D anomaly detection targets the detection and localization of defects in 3D point clouds trained solely on normal data. While a unified model improves scalability by learning across multiple categories, it often suffers from Inter-Category Entanglement (ICE)-where latent features from different categories overlap, causing the model to adopt incorrect semantic priors during reconstruction and ultimately yielding unreliable anomaly scores. To address this issue, we propose the Semantically Disentangled Unified Model for 3D Anomaly Detection, which reconstructs features conditioned on disentangled semantic representations. Our framework consists of three key components: (i) Coarse-to-Fine Global Tokenization for forming instance-level semantic identity, (ii) Category-Conditioned Contrastive Learning for disentangling category semantics, and (iii) a Geometry-Guided Decoder for semantically consistent reconstruction. Extensive experiments on Real3D-AD and Anomaly-ShapeNet demonstrate that our method achieves state-of-the-art for both unified and category-specific models, improving object-level AUROC by 2.8% and 9.1%, respectively, while enhancing the reliability of unified 3D anomaly detection.

Related papers

• Open-Vocabulary 3D Object Detection with Co-Distillation Discovery and Dual Guidance Robust Training [15.510191654885778]
  3D object detection has gained increasing attention for its ability to detect unseen objects in 3D scenes.<n>Existing approaches typically adopt a two-stage pipeline that first discovers novel objects using foundation models and then trains a 3D-OVD model based on these discovered objects.<n>We advocate for improving both the reliability of novel object discovery and the robustness of model training, and propose an innovative framework.
  arXiv  Detail & Related papers  (2026-08-20T12:47:40Z)
• Anomaly Factory 3D: A Modular Framework for Diverse Pseudo-Anomaly Synthesis in Unsupervised 3D Anomaly Detection [0.0]
  Anomaly Factory 3D (AF3AD) is a modular framework that synthesizes diverse pseudo-anomalies from normal point clouds.<n> AF3AD is designed as a standalone synthesis tool to facilitate adoption across different 3D anomaly detection paradigms.
  arXiv  Detail & Related papers  (2026-06-28T03:55:44Z)
• Point Cloud Diffusion with Global and Local Reconstruction for Instance-Level 3D Anomaly Detection [53.26344422459608]
  We propose textbfPCDiff, a point cloud diffusion framework for instance-level 3D anomaly generation and detection.<n>In the generation phase, an instance-level multi-modal attention is embedded into the generation framework, where anomalies are conditioned with texture gradient, image patch, text and mask.<n>In the detection phase, a joint local-global reconstruction algorithm is introduced to ensure local anomaly restoration and global geometric consistency.
  arXiv  Detail & Related papers  (2026-06-24T12:11:05Z)
• 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)
• Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly Detection [24.451730437527804]
  3D shape anomaly detection is a crucial task for industrial inspection and geometric analysis.<n>Existing deep learning approaches typically learn representations of normal shapes and identify anomalies.<n>We propose a hierarchical point-patch anomaly scoring network that jointly models regional part features and local point features.
  arXiv  Detail & Related papers  (2026-04-05T05:37:27Z)
• CASL: Curvature-Augmented Self-supervised Learning for 3D Anomaly Detection [49.74534277563012]
  We propose a Curvature-Augmented Self-supervised Learning (CASL) framework based on a reconstruction paradigm.<n>Our approach introduces multi-scale curvature prompts to guide the decoder in predicting the spatial coordinates of each point.<n>It achieves leading detection performance through straightforward anomaly classification fine-tuning.
  arXiv  Detail & Related papers  (2025-11-17T02:58:09Z)
• Stereo-based 3D Anomaly Object Detection for Autonomous Driving: A New Dataset and Baseline [10.933880236559604]
  3D detection technology is widely used in the field of autonomous driving.<n>For rare anomaly categories that appear on the road, 3D detection models often misdetect or fail to detect anomalies.<n>This paper proposes a Stereo-based 3D Anomaly object Detection (S3AD) algorithm.
  arXiv  Detail & Related papers  (2025-07-12T09:10:29Z)
• Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition [63.55828203989405]
  We introduce a novel Topology-Aware Modeling (TAM) framework for Sim2Real UDA on object point clouds.<n>Our approach mitigates the domain gap by leveraging global spatial topology, characterized by low-level, high-frequency 3D structures.<n>We propose an advanced self-training strategy that combines cross-domain contrastive learning with self-training.
  arXiv  Detail & Related papers  (2025-06-26T11:53:59Z)
• Towards Zero-shot 3D Anomaly Localization [58.62650061201283]
  3DzAL is a novel patch-level contrastive learning framework for 3D anomaly detection and localization.<n>We show that 3DzAL outperforms the state-of-the-art anomaly detection and localization performance.
  arXiv  Detail & Related papers  (2024-12-05T16:25:27Z)
• R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection [12.207437451118036]
  3D anomaly detection plays a crucial role in monitoring parts for localized inherent defects in precision manufacturing. Embedding-based and reconstruction-based approaches are among the most popular and successful methods. We propose R3D-AD, reconstructing anomalous point clouds by diffusion model for precise 3D anomaly detection.
  arXiv  Detail & Related papers  (2024-07-15T16:10:58Z)
• 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)
• NOVUM: Neural Object Volumes for Robust Object Classification [22.411611823528272]
  We show that explicitly integrating 3D compositional object representations into deep networks for image classification leads to a largely enhanced generalization in out-of-distribution scenarios. In particular, we introduce a novel architecture, referred to as NOVUM, that consists of a feature extractor and a neural object volume for every target object class. Our experiments show that NOVUM offers intriguing advantages over standard architectures due to the 3D compositional structure of the object representation.
  arXiv  Detail & Related papers  (2023-05-24T03:20:09Z)
• Stereo Neural Vernier Caliper [57.187088191829886]
  We propose a new object-centric framework for learning-based stereo 3D object detection. We tackle a problem of how to predict a refined update given an initial 3D cuboid guess. Our approach achieves state-of-the-art performance on the KITTI benchmark.
  arXiv  Detail & Related papers  (2022-03-21T14:36:07Z)

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.