Pith. sign in

REVIEW 4 cited by

AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusion

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.19444 v2 pith:EI4FGNZQ submitted 2024-04-30 cs.CV

Jie Hu , Yawen Huang , Yilin Lu , Guoyang Xie , Guannan Jiang , Yefeng Zheng , Zhichao Lu This is my paper
classification cs.CV
keywords anomalyxfusionmoduleabnormalanomaliesanomalyinformationmvtecsamples
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Anomaly synthesis is one of the effective methods to augment abnormal samples for training. However, current anomaly synthesis methods predominantly rely on texture information as input, which limits the fidelity of synthesized abnormal samples. Because texture information is insufficient to correctly depict the pattern of anomalies, especially for logical anomalies. To surmount this obstacle, we present the AnomalyXFusion framework, designed to harness multi-modality information to enhance the quality of synthesized abnormal samples. The AnomalyXFusion framework comprises two distinct yet synergistic modules: the Multi-modal In-Fusion (MIF) module and the Dynamic Dif-Fusion (DDF) module. The MIF module refines modality alignment by aggregating and integrating various modality features into a unified embedding space, termed X-embedding, which includes image, text, and mask features. Concurrently, the DDF module facilitates controlled generation through an adaptive adjustment of X-embedding conditioned on the diffusion steps. In addition, to reveal the multi-modality representational power of AnomalyXFusion, we propose a new dataset, called MVTec Caption. More precisely, MVTec Caption extends 2.2k accurate image-mask-text annotations for the MVTec AD and LOCO datasets. Comprehensive evaluations demonstrate the effectiveness of AnomalyXFusion, especially regarding the fidelity and diversity for logical anomalies. Project page: http:github.com/hujiecpp/MVTec-Caption

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. OSAGEN: Object-Aware Mask Priors and Multistage Decoupled Diffusion for Industrial Anomaly Generation

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A three-stage decoupled diffusion generator with query-biased object-aware masks and inference-time spatial control sets new SOTA on synthetic-to-real anomaly localization.

  2. Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    TopoTTA integrates persistent homology into test-time adaptation to derive topological pseudo-labels from anomaly maps, improving segmentation by an average 15% F1 on six benchmarks while generalizing across 2D and 3D data.

  3. One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Control

    cs.CV 2026-03 unverdicted novelty 6.0 of 10

    O2MAG generates high-fidelity text-guided anomalies from a single image without training by manipulating self-attention in diffusion models with anomaly masks and dual enhancements.

  4. Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection

    cs.CV 2025-07 conditional novelty 6.0 of 10

    GAA synthesizes aligned anomaly image-mask pairs from few examples using decomposed concept embeddings and region-guided masks, improving downstream anomaly localization and classification on MVTec AD and LOCO.

Pith tools