mlsanityData to 13 Oct 2026

SplatPose+: Real-time Image-Based Pose-Agnostic 3D Anomaly Detection

arXiv 2410.12080 ↗First posted 15 Oct 2024cs.CVcited by 11

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

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,170
  2. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,725
  3. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,316
  4. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 979
  5. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
  6. 2023LightGlue: Local Feature Matching at Light Speedcited by 588
  7. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 557
  8. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 381
  9. 2020DISK: Learning local features with policy gradientcited by 310
  10. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  11. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  12. 2021Explainable Deep Few-shot Anomaly Detection with Deviation Networkscited by 69
3 more
  1. 2023PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detectioncited by 46
  2. 2024SplatPose & Detect: Pose-Agnostic 3D Anomaly Detectioncited by 25
  3. 2016SIFT: An Algorithm for Extracting Structural Information From Taxonomiescited by 1

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 5; 2026: 6.

11 papers.