Organizations: National Taiwan University Taipei, Taiwan · National Taiwan Normal University Taipei, Taiwan · Mitsubishi Electric Research Laboratories (MERL) Cambridge, MA, USA · VinUniversity Hanoi, Vietnam · Microsoft Taiwan Corporation Taipei, Taiwan · National Taiwan University of Science and Technology Taipei, Taiwan
Multi-view anomaly detection (MvAD) detects defects by exploiting complementary observations from multiple camera viewpoints. The central challenge is to fuse views with sufficient geometric awareness while remaining scalable to multi-class industrial settings. Existing methods typically fall into two extremes: voxel-based fusion provides explicit geometric alignment but requires costly 3D construction and class-specific assumptions, whereas lightweight patch-based fusion is efficient but relies on discrete candidate matching and lacks continuous cross-view correspondence. In this paper, we propose GeoMAD, a unified multi-view, multi-class AD framework that addresses both geometric correspondence deficiency and distributional inconsistency. Our Cross-view Deformable Fusion Module (CDFM) learns content-adaptive, view-pair-specific sampling offsets directly on 2D feature maps and arranges them across a multi-scale window pyramid with image-global reference sampling, enabling hierarchical cross-view correspondence without camera calibration, voxel construction, or class-specific 3D supervision. We further introduce Distributional View Alignment (DVA), a self-supervised cross-view regularization loss that aligns each view's bottleneck distribution against a per-instance view-centric target, enforcing global consistency without pixel-level correspondence. Together, CDFM and DVA bridge local geometric correspondence and global distributional consistency, providing geometry-aware and distribution-consistent fusion while preserving the efficiency of 2D feature-space learning. Extensive experiments on Real-IAD and MANTA-Tiny show that GeoMAD achieves strong detection and localization performance in unified MvAD.
Figures & tables
Figure 1: GeoMAD \xspace combines Cross-view Deformable Fusion Module (CDFM) and Distributional View Alignment (DVA) to achieve geometry-aware and distribution-consistent fusion directly in 2D feature space, addressing key limitations of existing methods [ 11 , 20 ] .
Method Properties
AD Categories
G0
G1
IDIF
MVAD
GeoMAD (ours) \xspace
Single model for all classes
✗
✓
✗
✓
✓
Designed for multi-view AD
✗
✗
✓
✓
✓
Learned 2D geometric correspondence
✗
✗
✗
✗
✓
Distributional view alignment
✗
✗
✗
✗
✓
Table 1: Characteristic comparison between GeoMAD (ours) \xspace and prior AD works. G0 denotes class-specific single-view AD methods [ 17 , 12 , 24 , 5 , 6 , 32 , 4 ] ; G1 denotes unified single-view AD methods [ 31 , 34 , 9 , 8 , 10 , 29 ] . IDIF [ 20 ] and MVAD [ 11 ] denote representative multi-view AD methods.
Figure 2: Overview of our proposed GeoMAD \xspace . Given multi-view input images, GeoMAD \xspace adopts a teacher-student architecture with the Cross-view Deformable Fusion Module (CDFM) for deformable cross-view feature fusion. Distributional View Alignment (DVA) mitigates distributional inconsistency by aligning bottleneck feature distributions across views. Multi-view anomaly scores are then aggregated for final detection.
Figure 3: The mechanism of CDFM. (a) CDFM predicts offsets Δq→r from the windowed query features and bilinearly samples reference keys and values at the deformed positions p+Δq→r . Each query view produces V−1 offset fields, so windowed queries can deformably attend to features anywhere in each reference view, coupling cheap query windowing with global key/value reach. (b) Details of the offset network.
Method
S-AUROC
S-AP
S-F1
I-AUROC
I-AP
I-F1
P-AUROC
P-AP
P-F1
P-AUPRO
RD4AD CVPR’22 [ 6 ]
78.3
63.7
68.3
80.5
59.5
62.4
91.8
29.1
34.7
78.8
UniAD NeurIPS’22 [ 31 ]
74.9
59.7
65.2
82.7
64.3
65.1
90.7
26.1
32.4
79.6
DeSTSeg CVPR’23 [ 37 ]
62.4
49.3
56.5
62.3
37.8
45.5
54.8
12.0
9.0
23.4
RealNet CVPR’24 [ 36 ]
55.1
40.9
51.7
57.3
31.8
41.3
50.0
10.3
4.4
15.1
MVAD TMM’25 [ 11 ]
85.0
76.5
73.8
85.2
69.9
67.9
93.7
32.7
38.5
80.7
GeoMAD (ours) \xspace
88.2
81.9
78.3
87.0
73.4
70.5
94.2
36.8
41.6
83.1
Table 2: Average performance comparison on MANTA-Tiny dataset. The best and second-best results are marked in bold and underlined .
Method
S-AUROC
S-AP
S-F1
I-AUROC
I-AP
I-F1
P-AUROC
P-AP
P-F1
P-AUPRO
RD4AD CVPR’22 [ 6 ]
85.7
92.4
87.7
83.0
79.6
74.4
97.3
25.8
33.5
90.4
UniAD NeurIPS’22 [ 31 ]
87.3
93.1
88.9
83.0
83.4
74.6
97.4
23.7
31.4
87.3
RD++ CVPR’23 [ 27 ]
87.0
93.3
88.2
83.7
80.9
74.9
97.7
25.8
33.5
90.0
SimpleNet CVPR’23 [ 17 ]
61.2
77.9
82.1
82.6
79.2
74.1
76.3
3.4
6.9
42.5
DeSTSeg CVPR’23 [ 37 ]
89.0
94.6
89.2
82.3
79.2
73.2
94.6
37.9
41.7
40.6
RealNet CVPR’24 [ 36 ]
72.0
87.1
82.5
65.2
65.4
62.7
60.5
27.2
24.9
28.7
Table 3: Average performance comparison on Real-IAD dataset. The best and second-best results are marked in bold and underlined .
Figure 4: Qualitative comparison on Real-IAD (left) and MANTA-Tiny (right). Each row shows one view of the same object instance ( V=5 views per sample). GeoMAD \xspace yields more spatially coherent localization with fewer false activations.
Dataset
CDFM
DVA
S-AUROC
S-AP
S-F1
I-AUROC
I-AP
I-F1
P-AUROC
P-AP
P-F1
P-AUPRO
MANTA-Tiny
✗
✗
78.3
63.7
68.3
80.5
59.5
62.4
91.8
29.1
34.7
78.9
✓
✗
87.8
81.4
77.7
86.6
72.7
70.0
94.0
36.0
40.9
82.4
✓
✓
88.2
81.9
78.3
87.0
73.4
70.5
94.2
36.8
41.6
83.1
Real-IAD
✗
✗
84.7
91.8
87.5
82.0
78.5
73.7
97.0
26.1
33.3
89.5
✓
✗
91.6
95.8
91.0
87.3
85.5
77.9
97.8
35.7
41.0
92.0
✓
✓
91.8
95.9
91.2
87.5
85.6
78.2
97.8
35.6
40.8
92.2
Table 4: Ablation study on CDFM and DVA. We evaluate the contribution of Cross-view Deformable Fusion Module (CDFM) and Distributional View Alignment (DVA) on MANTA-Tiny and Real-IAD, reporting sample-level (S), image-level (I), and pixel-level (P) metrics. Bold indicates the best result and underlined indicates the second best.
Kernel Size
S-AUROC
S-AP
S-F1
I-AUROC
I-AP
I-F1
P-AUROC
P-AP
P-F1
P-AUPRO
-
91.3
95.7
90.9
87.0
85.1
77.6
97.8
35.5
40.5
91.6
{3}
91.0
95.5
90.7
86.8
85.0
77.4
97.8
35.2
40.3
91.4
{5}
91.6
95.8
91.0
87.4
85.5
78.0
97.8
36.1
41.2
92.0
{7}
91.8
95.9
91.2
87.5
85.6
78.2
97.8
35.6
40.8
92.2
{9}
92.0
96.0
91.2
87.3
85.3
77.9
97.8
35.1
40.5
92.0
{5,7}
91.0
95.5
90.7
86.8
84.9
77.4
97.8
35.4
40.5
91.4
Table 5: Impact of smoothing kernel size in CDFM. We compare single-kernel sizes {3, 5, 7, 9} and a multi-kernel variant {5, 7} against a no-smoothing baseline (denoted “-”). The best and second-best results are marked in bold and underlined .
DVA Type
S-AUROC
S-AP
S-F1
I-AUROC
I-AP
I-F1
P-AUROC
P-AP
P-F1
P-AUPRO
View Pair
91.6
95.8
91.2
86.9
84.8
77.4
97.8
34.3
39.8
91.7
View Centric
91.8
95.9
91.2
87.5
85.6
78.2
97.8
35.6
40.8
92.2
Table 6: Alignment target in DVA. Comparison between pairwise alignment (View Pair) and view-centric alignment toward a shared per-instance centroid (View Centric).
Views
S-AUROC
S-AP
S-F1
I-AUROC
I-AP
I-F1
P-AUROC
P-AP
P-F1
P-AUPRO
5 (default)
91.8
95.9
91.2
87.5
85.6
78.2
97.8
35.6
40.8
92.2
4
90.9
95.5
90.4
87.2
85.3
78.0
97.7
35.5
40.8
91.9
3
89.1
94.7
89.1
86.9
84.8
77.5
97.5
35.3
40.6
91.8
2
85.5
92.9
87.3
86.7
83.4
76.5
97.1
34.2
39.6
91.5
Table 7: Robustness to missing views on the Real-IAD dataset. We evaluate model performance when reducing the number of available views from the default 5 down to 2 at inference time, using the model trained with all 5 views.
Method
Parameters
FLOPs
Train Memory
RD4AD CVPR’22 [ 6 ]
80.61M
142.0G
11,614M
UniAD NeurIPS’22 [ 31 ]
24.52M
16.8G
7,324M
ViTAD CVIU’25 [ 34 ]
38.6M
48.3G
4,842M
MambaAD NIPS’24 [ 9 ]
25.7M
41.5G
28,994M
MVAD TMM’25 [ 11 ]
18.4M
45.0G
6,744M
GeoMAD (ours) \xspace
19.0M
46.8G
8,310M
Table 8: Computational efficiency comparison. Parameters, FLOPs, and training memory of GeoMAD \xspace against representative SOTA methods.
Multi-view anomaly detection aims to identify surface defects on complex objects using observations captured from multiple viewpoints. However, existing unsupervised methods often suffer from feature inconsistency arising from viewpoint variations and modality discrepancies. To address these challenges, we propose a Semantic and Geometric Alignment Network (SGANet), a unified framework for multimodal multi-view anomaly detection that effectively combines semantic and geometric alignment to learn physically coherent feature representations across viewpoints and modalities. SGANet consists of three key components. The Selective Cross-view Feature Refinement Module (SCFRM) selectively aggregates informative patch features from adjacent views to enhance cross-view feature interaction. The Semantic-Structural Patch Alignment (SSPA) enforces semantic alignment across modalities while maintaining structural consistency under viewpoint transformations. The Multi-View Geometric Alignment (MVGA) further aligns geometrically corresponding patches across viewpoints. By jointly modeling feature interaction, semantic and structural consistency, and global geometric correspondence, SGANet effectively enhances anomaly detection performance in multimodal multi-view settings. Extensive experiments on the SiM3D and Eyecandies datasets demonstrate that SGANet achieves state-of-the-art performance in both anomaly detection and localization, validating its effectiveness in realistic industrial scenarios.
Letian Bai, Chengyu Tao, Juan Du
Smart Manufacturing Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, 511453, China · College of Mechanical and Vehicle Engineering, Hunan University, Changsha, 410082, China · The Hong Kong University of Science and Technology, Hong Kong SAR, 999077, China
In multi-view anomaly detection, more cross-view information can actually hurt. When multiple inspection views are naively fused in a reconstruction-based pipeline, normal cues from intact views propagate to the decoder, which faithfully reconstructs anomalous regions, collapsing the reconstruction gap the detector depends on. We call this failure mode cross-view information leakage and show that effective multi-view fusion must explicitly restrict the information reaching the decoder. Building on this insight, we present GLAD(Global-Local Attention Driven framework), the first framework combining vision foundation model features with local and global cross-view fusion for multi-view anomaly detection. The Multi-view Merging Attention (MMA) module performs local cross-view fusion at linear complexity with learnable view importance weighting and token-wise gating, letting each view selectively incorporate fine-grained evidence from other views at O(N) cost. The Object-Guided Attention (OGA) module captures global context by aggregating class tokens from all views into a single object-level representation and broadcasting it back to patch tokens via temperature-scaled sigmoid gating, replacing the original patch representations rather than adding a residual to preserve the reconstruction gap. Experiments on Real-IAD and MANTA-Tiny show that GLAD outperforms state-of-the-art methods across sample-, image-, and pixel-level metrics, confirming that principled information restriction is key to multi-view anomaly reasoning.
Shang-Fu Chen, Kuan-Chuan Peng, Jhih-Ciang Wu +2
National Taiwan University Taipei, Taiwan · Mitsubishi Electric Research Laboratories (MERL) Cambridge, MA, USA · National Taiwan Normal University Taipei, Taiwan +2
Existing Multi-view Anomaly Detection (MAD) methods assume that all views are completely available and model each view separately. However, in real industrial scenarios, information in the view may be missing due to faults such as occlusion, which leads to the performance degradation of existing methods due to the lack of a multi-view consistency prior. To address this, we explored a more challenging task: Incomplete Multi-View Anomaly Detection (IMVAD), in which some areas of each view were masked. We proposed a pipeline for automatically generating the IMVAD dataset and generated the RIMAD dataset based on the Real-IAD dataset through this pipeline. In addition, in order to effectively utilize the information of multiple views in the absence of view information, we propose IMMoE, which consists of two key modules: (1) Multi-View Expert Fusion (MVEF) effectively fuses multi-view information through a multi-view expert network and guides the reconstruction of a single view; (2) Local Anomaly Enhancement Encoder (LAEE) effectively prevents the model from overfitting the mask region by applying dropout to local features. Our method achieves state-of-the-art performance on both the RIMAD and Real-IAD datasets, especially on RIMAD, we have increased the pixel-level and image-level metrics by 11.8% and 2.8%, respectively. Our source code is available at https://github.com/HULEI7/IMMoE
Lei Hu
South China University of Technology, Guangzhou, China