Papers › Multimodal Industrial Anomaly Detection via Hybrid Fusion

Multimodal Industrial Anomaly Detection via Hybrid Fusion

1 Mar 2023CVPR 2023 1arXiv:2303.00601archive 2025-07-28

Yue Wang, Jinlong Peng, Jiangning Zhang, Ran Yi, Yabiao Wang, Chengjie Wang

2D-based Industrial Anomaly Detection has been widely discussed, however, multimodal industrial anomaly detection based on 3D point clouds and RGB images still has many untouched fields. Existing multimodal industrial anomaly detection methods directly concatenate the multimodal features, which leads to a strong disturbance between features and harms the detection performance. In this paper, we propose Multi-3D-Memory (M3DM), a novel multimodal anomaly detection method with hybrid fusion scheme: firstly, we design an unsupervised feature fusion with patch-wise contrastive learning to encourage the interaction of different modal features; secondly, we use a decision layer fusion with multiple memory banks to avoid loss of information and additional novelty classifiers to make the final decision. We further propose a point feature alignment operation to better align the point cloud and RGB features. Extensive experiments show that our multimodal industrial anomaly detection model outperforms the state-of-the-art (SOTA) methods on both detection and segmentation precision on MVTec-3D AD dataset. Code is available at https://github.com/nomewang/M3DM.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2303.00601")

Code

Syntology Ran 3 of 9 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

nomewang/m3dm officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested; 3 ran; 2 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2ran · honoured contract
1ran
6unverified

Licence: 0 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from nomewang/M3DM. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

adjust_learning_rate nomewang/M3DM/utils/lr_sched.py official repository ran · honoured contract MIT (permissive) · bd3578806ecf5ac2 · report
all_reduce_mean nomewang/M3DM/utils/misc.py official repository ran fingerprinted MIT (permissive) · 3dc19396537db789 · report
pc_normalize nomewang/M3DM/models/pointnet2_utils.py official repository ran · honoured contract fingerprinted MIT (permissive) · ec413739d406e611 · report
collect_anomaly_scores nomewang/M3DM/utils/au_pro_util.py official repository unverified MIT (permissive) · 18c9bfa7e94951e9 · report
compute_pro nomewang/M3DM/utils/au_pro_util.py official repository unverified MIT (permissive) · 49b5692178958afe · report
get_data_loader nomewang/M3DM/dataset.py official repository unverified MIT (permissive) · 4d4e430ec99ab841 · report
square_distance nomewang/M3DM/models/pointnet2_utils.py official repository unverified MIT (permissive) · 6ddec81b1d23c787 · report
timeit nomewang/M3DM/models/pointnet2_utils.py official repository unverified MIT (permissive) · b1227ddb721e2999 · report
trapezoid nomewang/M3DM/utils/au_pro_util.py official repository unverified MIT (permissive) · 9d72c1f1f0d6dea4 · report

Tasks

3D Anomaly DetectionAnomaly DetectionContrastive LearningRGB+3D Anomaly Detection and Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Anomaly Detection Anomaly-ShapeNet10 M3DM O-AUROC 0.574 #4 of 7 Archive leaderboard report
3D Anomaly Detection Anomaly-ShapeNet10 M3DM P-AUROC 0.648 #4 of 7 Archive leaderboard report
3D Anomaly Detection Real 3D-AD M3DM (PointMAE) Mean Performance of P. and O. 0.5945 #16 of 19 Archive leaderboard report
3D Anomaly Detection Real 3D-AD M3DM (PointMAE) Object AUROC 0.552 #16 of 19 Archive leaderboard report
3D Anomaly Detection Real 3D-AD M3DM (PointMAE) Point AUROC 0.637 #16 of 19 Archive leaderboard report
3D Anomaly Detection Real 3D-AD M3DM (PointBERT) Mean Performance of P. and O. 0.587 #18 of 19 Archive leaderboard report
3D Anomaly Detection Real 3D-AD M3DM (PointBERT) Object AUROC 0.538 #18 of 19 Archive leaderboard report
3D Anomaly Detection Real 3D-AD M3DM (PointBERT) Point AUROC 0.636 #18 of 19 Archive leaderboard report
RGB+3D Anomaly Detection and Segmentation MVTEC 3D-AD M3DM Detection AUCROC 0.945 #4 of 9 Archive leaderboard report
RGB+3D Anomaly Detection and Segmentation MVTEC 3D-AD M3DM Segmentation AUCROC 0.992 #4 of 9 Archive leaderboard report
RGB+3D Anomaly Detection and Segmentation MVTEC 3D-AD M3DM Segmentation AUPRO 0.964 #4 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ALIGNContrastive Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections