6 February 2026 in IEEE Access
The reliability of automated industrial defect detection systems is fundamentally constrained by the long-tail distribution and scarcity of anomalous samples. This limitation is further intensified by the topological–textural conflict: rare defects often exhibit high-frequency, stochastic morphologies that are topologically incompatible with the highly structured and repetitive background manifolds of industrial components. To address this challenge, this paper proposes the Dual-Manifold Gradient Rectification (DMGR) framework. Unlike prior approaches that rely on heuristic blending or monolithic inpainting, DMGR reformulates defect synthesis as a deterministic trajectory rectification process. Specifically, a global diffusion model establishes a Base Structural Field, while a specialized local defect model provides a Rectification Field governed by manifold consistency constraints. To ensure physical plausibility, a Physics-Grounded Spectral-Spatial Alignment mechanism is introduced, which dynamically injects high-frequency defect details into the global trajectory via uncertainty-adaptive spatial gating. Furthermore, an Asymmetric Collaborative Evolution strategy is employed to coordinate the interaction between Structural Anchoring and Textural Resonance, thereby effectively harmonizing global topology with local defect fidelity. Experimental results on a PCB defect dataset demonstrate that DMGR achieves favorable semantic coherence and spectral authenticity. Augmenting the training set with the synthesized samples yields a 10.3 percent relative improvement in the detector’s mean Average Precision evaluated over multiple intersection-over-union thresholds. Notably, the proposed framework exhibits strong scalability, maintaining consistent performance gains even when the training data are augmented by a factor of six, which establishes DMGR as a practical and effective solution for addressing complex industrial anomalies. The code and data are available at https://github.com/weihang-luo/DMGR
5 January 2026 in IEEE Transactions on Circuits and Systems for Video Technology
Automated Visual Inspection is a cornerstone of modern manufacturing, yet the development of robust deep learning models is frequently impeded by the scarcity and imbalance of training data. This challenge is particularly acute for industrial defects, which often manifest as subtle anomalies intrinsically linked to complex, structured backgrounds. To address this challenge, CRG-DefectDiffuser is proposed as a collaborative generative framework for high-fidelity defect synthesis. At its core lies the Collaborative Refinement Guidance (CRG) mechanism, which orchestrates two specialized diffusion models: one trained on abundant defect-free images to master background context, and another trained on scarce defect patches to encode fine-grained defect semantics. The CRG mechanism steers the synthesis by dynamically generating a guidance map, which is refined through a four-stage process to ensure that morphologically accurate defects are seamlessly integrated into the appropriate background context. Augmenting training data with our method boosts the defect detection mAP@50-95 from a baseline of 0.496 to 0.557, corresponding to a 12.3 percentage point relative improvement. The framework also demonstrates superior scalability, with performance gains continuing up to the three-fold data augmentation evaluated in our experiments, a point where competing methods often falter. These results establish CRG-DefectDiffuser as an effective and practical solution to data scarcity in industrial visual inspection, with strong potential for generalization across diverse manufacturing scenarios. The source code is publicly available at https://github.com/weihang-luo/ CRG-DefectDiffuser.
13 March 2026 in Measurement