# 2D_3D Feature Fusion via Cross-Modal Latent Synthesis and Attention Guided Restoration for Industrial Anomaly Detection

arXiv: https://arxiv.org/abs/2510.21793 · HTML: https://mlsanity.com/paper/2510.21793/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 34 references that are in the map.
- First posted on arXiv 20 Oct 2025.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [Multiresolution Knowledge Distillation for Anomaly Detection](https://mlsanity.com/paper/2011.11108/) (2020)
- [Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows](https://mlsanity.com/paper/2008.12577/) (2020)
- [The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization](https://mlsanity.com/paper/2112.09045/) (2021)
- [Deep Industrial Image Anomaly Detection: A Survey](https://mlsanity.com/paper/2301.11514/) (2023)
- [Multimodal Industrial Anomaly Detection via Hybrid Fusion](https://mlsanity.com/paper/2303.00601/) (2023)
- [Asymmetric Student-Teacher Networks for Industrial Anomaly Detection](https://mlsanity.com/paper/2210.07829/) (2022)
- [Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection](https://mlsanity.com/paper/2203.05550/) (2022)
- [DSR -- A dual subspace re-projection network for surface anomaly detection](https://mlsanity.com/paper/2208.01521/) (2022)
- [The Eyecandies Dataset for Unsupervised Multimodal Anomaly Detection and Localization](https://mlsanity.com/paper/2210.04570/) (2022)
- [Anomaly Detection with Conditioned Denoising Diffusion Models](https://mlsanity.com/paper/2305.15956/) (2023)
- [DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation](https://mlsanity.com/paper/2012.07122/) (2020)
- [Surface Reconstruction from Point Clouds by Learning Predictive Context Priors](https://mlsanity.com/paper/2204.11015/) (2022)
- [Multimodal Industrial Anomaly Detection by Crossmodal Feature Mapping](https://mlsanity.com/paper/2312.04521/) (2023)
- [CAINNFlow: Convolutional block Attention modules and Invertible Neural Networks Flow for anomaly detection and localization tasks](https://mlsanity.com/paper/2206.01992/) (2022)
- [DAS3D: Dual-modality Anomaly Synthesis for 3D Anomaly Detection](https://mlsanity.com/paper/2410.09821/) (2024)
- [Locally-Focused Face Representation for Sketch-to-Image Generation Using Noise-Induced Refinement](https://mlsanity.com/paper/2411.19005/) (2024)
- [An Improved Fault Diagnosis Strategy for Induction Motors Using Weighted Probability Ensemble Deep Learning](https://mlsanity.com/paper/2412.18249/) (2024)

## Built on by (most cited first, 4 of 4)

- [Test-Time Adaptation for Anomaly Segmentation via Topology-Aware Optimal Transport Chaining](https://mlsanity.com/paper/2601.20333/) (2026)
- [CMDS-AD: Cross-Modal Dual-Stream Decoupling for Few-Shot Anomaly Detection](https://mlsanity.com/paper/2606.20300/) (2026)
- [Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation](https://mlsanity.com/paper/2606.28268/) (2026)
- [Multi-Modal Anomaly Detection: A Survey](https://mlsanity.com/paper/2608.24937/) (2026)

## Abstract (arXiv)

Industrial anomaly detection (IAD) increasingly benefits from integrating 2D and 3D data, but robust cross-modal fusion remains challenging. We propose a novel unsupervised framework, Multi-Modal Attention-Driven Fusion Restoration (MAFR), which synthesises a unified latent space from RGB images and point clouds using a shared fusion encoder, followed by attention-guided, modality-specific decoders. Anomalies are localised by measuring reconstruction errors between input features and their restored counterparts. Evaluations on the MVTec 3D-AD and Eyecandies benchmarks demonstrate that MAFR achieves state-of-the-art results, with a mean I-AUROC of 0.972 and 0.901, respectively. The framework also exhibits strong performance in few-shot learning settings, and ablation studies confirm the critical roles of the fusion architecture and composite loss. MAFR offers a principled approach for fusing visual and geometric information, advancing the robustness and accuracy of industrial anomaly detection. Code is available at https://github.com/adabrh/MAFR