SplatPose+: Real-time Image-Based Pose-Agnostic 3D Anomaly Detection
Not on the map. Why?
Abstract (arXiv)
Image-based Pose-Agnostic 3D Anomaly Detection is an important task that has emerged in industrial quality control. This task seeks to find anomalies from query images of a tested object given a set of reference images of an anomaly-free object. The challenge is that the query views (a.k.a poses) are unknown and can be different from the reference views. Currently, new methods such as OmniposeAD and SplatPose have emerged to bridge the gap by synthesizing pseudo reference images at the query views for pixel-to-pixel comparison. However, none of these methods can infer in real-time, which is critical in industrial quality control for massive production. For this reason, we propose SplatPose+, which employs a hybrid representation consisting of a Structure from Motion (SfM) model for localization and a 3D Gaussian Splatting (3DGS) model for Novel View Synthesis. Although our proposed pipeline requires the computation of an additional SfM model, it offers real-time inference speeds and faster training compared to SplatPose. Quality-wise, we achieved a new SOTA on the Pose-agnostic Anomaly Detection benchmark with the Multi-Pose Anomaly Detection (MAD-SIM) dataset.
Key facts. Cited by 11 papers in the map (data through 13 Oct 2026). Builds on 15 of its 21 references that are in the map. First posted on arXiv 15 Oct 2024.
Builds on
15 of 21 references.
References · 15
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,170
- 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,725
- 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,316
- 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 979
- 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
- 2023LightGlue: Local Feature Matching at Light Speedcited by 588
- 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 557
- 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 381
- 2020DISK: Learning local features with policy gradientcited by 310
- 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
- 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
- 2021Explainable Deep Few-shot Anomaly Detection with Deviation Networkscited by 69
3 more
Built on by
Citing papers per year: 2025: 5; 2026: 6.
11 papers.
- 2025Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detectioncited by 11
- 2026Predictive Photometric Uncertainty in Gaussian Splatting for Novel View Synthesiscited by 5
- 2025Fence Theorem: Towards Dual-Objective Semantic-Structure Isolation in Preprocessing Phase for 3D Anomaly Detectioncited by 4
- 2025Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detectioncited by 4
- 2025Changes in Real Time: Online Scene Change Detection with Multi-View Fusioncited by 3
- 2026From Pixels to Primitives: Scene Change Detection in 3D Gaussian Splattingcited by 3
- 20263D Gaussian Splatting for Annular Dark Field Scanning Transmission Electron Microscopy Tomography Reconstructioncited by 1
- 2026PlenoCI: Plenoptic CharacterIstics for View Dependence Aware Change Classificationcited by 1
- 2025Mentor3AD: Feature Reconstruction-based 3D Anomaly Detection via Multi-modality Mentor Learningcited by 0
- 2026Learning Discriminative Signed Distance Functions from Multi-scale Level-of-detail Features for 3D Anomaly Detectioncited by 0
- 2026PADFormer: Pose-agnostic Anomaly Detection from Sparse View Imagescited by 0
- 2026PlenoCI: Plenoptic CharacterIstics for View Dependence Aware Change Classification24 Sep 2026
- 2026PADFormer: Pose-agnostic Anomaly Detection from Sparse View Images4 Aug 2026
- 2026From Pixels to Primitives: Scene Change Detection in 3D Gaussian Splatting8 May 2026
- 2026Learning Discriminative Signed Distance Functions from Multi-scale Level-of-detail Features for 3D Anomaly Detection5 May 2026
- 20263D Gaussian Splatting for Annular Dark Field Scanning Transmission Electron Microscopy Tomography Reconstruction6 Apr 2026
- 2026Predictive Photometric Uncertainty in Gaussian Splatting for Novel View Synthesis24 Mar 2026
- 2025Changes in Real Time: Online Scene Change Detection with Multi-View Fusion15 Nov 2025
- 2025Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detection5 Jul 2025
- 2025Mentor3AD: Feature Reconstruction-based 3D Anomaly Detection via Multi-modality Mentor Learning27 May 2025
- 2025Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detection9 May 2025
- 2025Fence Theorem: Towards Dual-Objective Semantic-Structure Isolation in Preprocessing Phase for 3D Anomaly Detection3 Mar 2025