PADFormer: Pose-agnostic Anomaly Detection from Sparse View Images

• URL: http://arxiv.org/abs/2608.04210v1
• Date: Tue, 04 Aug 2026 20:23:34 GMT
• Title: PADFormer: Pose-agnostic Anomaly Detection from Sparse View Images
• Abstract summary: Pose-agnostic Anomaly Detection (PAD) remains challenging as anomalies can appear under arbitrary viewpoints.<n>We propose PADFormer, a novel image-space approach that leverages Vision Transformer (ViT) to directly reconstruct anomaly-free versions of query images.<n> PAD achieves state-of-the-art results on the PAD benchmark while maintaining comparable performance on classic few-shot anomaly detection tasks.
• Score: 40.540633292445925
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pose-agnostic Anomaly Detection (PAD) remains challenging as anomalies can appear under arbitrary viewpoints, requiring methods to handle significant pose variations. Existing approaches rely on complex 3D reconstruction, which are computationally expensive and require extensive multi-view data. We propose PADFormer, a novel image-space approach that leverages Vision Transformer (ViT) to directly reconstruct anomaly-free versions of query images while preserving pose information. Our key insight is to adapt cross-view masked reconstruction for anomaly detection through training exclusively on normal data, combined with dynamic patch selection and spatial alignment mechanisms that enable effective learning from sparse reference views under significant pose variations. During inference, we perform multiple forward passes with different masking patterns to generate an ensemble of anomaly-free reconstructions, ensuring comprehensive coverage of the query image. Anomalies are detected by comparing these reconstructions with the query image. PADFormer achieves state-of-the-art results on the PAD benchmark while maintaining comparable performance on classic few-shot anomaly detection (FSAD) tasks, demonstrating superior efficiency and generalization without requiring 3D reconstruction.

Related papers

• Visual Prompting Meets Feature Reconstruction-Based Anomaly Detection with Dual-Teacher Supervision [7.548589503544904]
  We introduce a visual prompting pipeline that isolates objects using foreground-background masking.<n>We also introduce a mechanism for unfreezing the teacher in student-teacher models to improve domain adaptability.<n>We achieve a 3.5 percentage point improvement over the previous state-of-the-art on the challenging AeBAD dataset.
  arXiv  Detail & Related papers  (2026-06-08T15:52:05Z)
• DisPOSE: Projected Polystochastic Diffusion for Self-Supervised Multi-View 3D Human Pose Estimation [58.47973015036709]
  DisPOSE is a self-supervised framework that approximates the inherently discrete multi-view person-assignment problem.<n>By employing differentiable Sinkhorn projections during denoising, our model learns to guide solutions toward valid and feasible assignments.<n>The proposed approach outperforms current state-of-the-art self-supervised methods on standard datasets.
  arXiv  Detail & Related papers  (2026-06-05T16:14:39Z)
• RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions [67.48495052903534]
  We propose a general and efficient multi-view feature enhancement module, RobustGS.<n>It substantially improves the robustness of feedforward 3DGS methods under various adverse imaging conditions.<n>The RobustGS module can be seamlessly integrated into existing pretrained pipelines in a plug-and-play manner.
  arXiv  Detail & Related papers  (2025-08-05T04:50:29Z)
• Bridging 3D Anomaly Localization and Repair via High-Quality Continuous Geometric Representation [1.4763103835215192]
  New framework integrates 3D anomaly detection and repair by learning a continuous, pose-invariant shape representation.<n>Experiments on Real3D-AD and Anomaly-ShapeNet demonstrate state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-05-30T10:11:49Z)
• FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction [69.63414788486578]
  FreeSplatter is a scalable feed-forward framework that generates high-quality 3D Gaussians from uncalibrated sparse-view images.<n>Our approach employs a streamlined transformer architecture where self-attention blocks facilitate information exchange.<n>We develop two specialized variants--for object-centric and scene-level reconstruction--trained on comprehensive datasets.
  arXiv  Detail & Related papers  (2024-12-12T18:52:53Z)
• Unsupervised Anomaly Detection via Masked Diffusion Posterior Sampling [8.887775968482208]
  diffusion models have shown promising applications for anomaly detection due to their powerful generative ability. This paper proposes a novel and highly-interpretable method named Masked Diffusion Posterior Sampling (MDPS) MDPS can achieve state-of-the-art performance in normal image reconstruction quality as well as anomaly detection and localization.
  arXiv  Detail & Related papers  (2024-04-27T13:13:27Z)
• 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)
• DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [55.48770333927732]
  We propose a Difusion-based Anomaly Detection (DiAD) framework for multi-class anomaly detection. It consists of a pixel-space autoencoder, a latent-space Semantic-Guided (SG) network with a connection to the stable diffusion's denoising network, and a feature-space pre-trained feature extractor. Experiments on MVTec-AD and VisA datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-12-11T18:38:28Z)
• Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection [54.041049052843604]
  We present STEMD, a novel end-to-end framework that enhances the DETR-like paradigm for multi-frame 3D object detection. First, to model the inter-object spatial interaction and complex temporal dependencies, we introduce the spatial-temporal graph attention network. Finally, it poses a challenge for the network to distinguish between the positive query and other highly similar queries that are not the best match.
  arXiv  Detail & Related papers  (2023-07-01T13:53:14Z)
• Masked Transformer for image Anomaly Localization [14.455765147827345]
  We propose a new model for image anomaly detection based on Vision Transformer architecture with patch masking. We show that multi-resolution patches and their collective embeddings provide a large improvement in the model's performance. The proposed model has been tested on popular anomaly detection datasets such as MVTec and head CT.
  arXiv  Detail & Related papers  (2022-10-27T15:30:48Z)
• CutPaste: Self-Supervised Learning for Anomaly Detection and Localization [59.719925639875036]
  We propose a framework for building anomaly detectors using normal training data only. We first learn self-supervised deep representations and then build a generative one-class classifier on learned representations. Our empirical study on MVTec anomaly detection dataset demonstrates the proposed algorithm is general to be able to detect various types of real-world defects.
  arXiv  Detail & Related papers  (2021-04-08T19:04:55Z)

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.