Double Helix Diffusion for Cross-Domain Anomaly Image Generation

• URL: http://arxiv.org/abs/2509.12787v1
• Date: Tue, 16 Sep 2025 08:06:07 GMT
• Title: Double Helix Diffusion for Cross-Domain Anomaly Image Generation
• Authors: Linchun Wu, Qin Zou, Xianbiao Qi, Bo Du, Zhongyuan Wang, Qingquan Li,
• Abstract summary: This paper introduces Double Helix Diffusion (DH-Diff), a novel cross-domain generative framework designed to simultaneously synthesize high-fidelity anomaly images and their pixel-level annotation masks.<n>DH-Diff employs a unique architecture inspired by a double helix, cycling through distinct modules for feature separation, connection, and merging.<n>Extensive experiments demonstrate that DH-Diff significantly outperforms state-of-the-art methods in diversity and authenticity, leading to significant improvements in downstream anomaly detection performance.
• Score: 47.093354259479234
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual anomaly inspection is critical in manufacturing, yet hampered by the scarcity of real anomaly samples for training robust detectors. Synthetic data generation presents a viable strategy for data augmentation; however, current methods remain constrained by two principal limitations: 1) the generation of anomalies that are structurally inconsistent with the normal background, and 2) the presence of undesirable feature entanglement between synthesized images and their corresponding annotation masks, which undermines the perceptual realism of the output. This paper introduces Double Helix Diffusion (DH-Diff), a novel cross-domain generative framework designed to simultaneously synthesize high-fidelity anomaly images and their pixel-level annotation masks, explicitly addressing these challenges. DH-Diff employs a unique architecture inspired by a double helix, cycling through distinct modules for feature separation, connection, and merging. Specifically, a domain-decoupled attention mechanism mitigates feature entanglement by enhancing image and annotation features independently, and meanwhile a semantic score map alignment module ensures structural authenticity by coherently integrating anomaly foregrounds. DH-Diff offers flexible control via text prompts and optional graphical guidance. Extensive experiments demonstrate that DH-Diff significantly outperforms state-of-the-art methods in diversity and authenticity, leading to significant improvements in downstream anomaly detection performance.

Related papers

• Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers [55.15722080205737]
  Edit2Perceive is a unified diffusion framework that adapts editing models for depth, normal, and matting.<n>Our single-step deterministic inference yields up to faster runtime while training on relatively small datasets.
  arXiv  Detail & Related papers  (2025-11-24T01:13:51Z)
• Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection [53.137651284042434]
  Anomaly inspection plays a vital role in industrial manufacturing, but the scarcity of anomaly samples limits the effectiveness of existing methods.<n>We propose Generate grained Anomaly (GAA), a region-guided, few-shot anomaly image-mask pair generation framework.<n>GAA generates realistic, diverse, and semantically aligned anomalies using only a small number of samples.
  arXiv  Detail & Related papers  (2025-07-13T12:56:59Z)
• Virtual-mask Informed Prior for Sparse-view Dual-Energy CT Reconstruction [9.118267161536087]
  We propose a dual-domain virtual-mask in-formed diffusion model for sparse-view reconstruction by leveraging the high inter-channel correlation in perturbations.<n> Experimental results indicated that the present method exhibits excellent performance across multiple datasets.
  arXiv  Detail & Related papers  (2025-04-10T13:54:26Z)
• Bi-Grid Reconstruction for Image Anomaly Detection [0.0]
  This paper introduces textbfGRAD: Bi-textbfGrid textbfReconstruction for Image textbfAnomaly textbfDetection.<n>It employs two continuous grids to enhance anomaly detection from both normal and abnormal perspectives.<n>It excels in overall accuracy and in discerning subtle differences, demonstrating its superiority over existing methods.
  arXiv  Detail & Related papers  (2025-04-01T10:06:38Z)
• FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion [63.87313550399871]
  Image-event joint depth estimation methods leverage complementary modalities for robust perception, yet face challenges in generalizability.<n>We propose Self-supervised Transfer (PST) and FrequencyDe-coupled Fusion module (FreDF)<n>PST establishes cross-modal knowledge transfer through latent space alignment with image foundation models.<n>FreDF explicitly decouples high-frequency edge features from low-frequency structural components, resolving modality-specific frequency mismatches.
  arXiv  Detail & Related papers  (2025-03-25T15:04:53Z)
• HFMF: Hierarchical Fusion Meets Multi-Stream Models for Deepfake Detection [4.908389661988192]
  HFMF is a comprehensive two-stage deepfake detection framework.<n>It integrates vision Transformers and convolutional nets through a hierarchical feature fusion mechanism.<n>We demonstrate that our architecture achieves superior performance across diverse dataset benchmarks.
  arXiv  Detail & Related papers  (2025-01-10T00:20:29Z)
• Cross-Modal Learning for Anomaly Detection in Complex Industrial Process: Methodology and Benchmark [19.376814754500625]
  Anomaly detection in complex industrial processes plays a pivotal role in ensuring efficient, stable, and secure operation. This paper proposes a cross-modal Transformer to facilitate anomaly detection by exploring the correlation between visual features (video) and process variables (current) in the context of the fused magnesium smelting process. We present a pioneering cross-modal benchmark of the fused magnesium smelting process, featuring synchronously acquired video and current data for over 2.2 million samples.
  arXiv  Detail & Related papers  (2024-06-13T11:40:06Z)
• Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection [59.34318192698142]
  We introduce a prior-less anomaly generation paradigm and develop an innovative unsupervised anomaly detection framework named GRAD. PatchDiff effectively expose various types of anomaly patterns. experiments on both MVTec AD and MVTec LOCO datasets also support the aforementioned observation.
  arXiv  Detail & Related papers  (2023-12-26T07:08:06Z)
• 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)
• Unsupervised Two-Stage Anomaly Detection [18.045265572566276]
  Anomaly detection from a single image is challenging since anomaly data is always rare and can be with highly unpredictable types. We propose a two-stage approach, which generates high-fidelity yet anomaly-free reconstructions. Our method outperforms state-of-the-arts on four anomaly detection datasets.
  arXiv  Detail & Related papers  (2021-03-22T08:57:27Z)

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.