The paper introduces Structured Defect Grounding (SDG), a method that treats text‑to‑image failure diagnosis as a structured set prediction problem, representing each defect as a tuple of location, type, reason, and importance. It presents SDG‑30K, a 30,000‑image dataset with box‑grounded annotations for four modern T2I generators, and a dedicated evaluation protocol, SDG‑Eval. Using a Vision‑Language Model as an SDG detector and a BoxFlow‑GRPO module, the authors demonstrate that SDG‑guided rewards improve diffusion model alignment and enable localized image refinement, positioning SDG as a unified interface for diagnosing and enhancing generative models.
Despite generating increasingly photorealistic images, text-to-image (T2I) models still exhibit localized, subtle, and structurally complex failures. Diagnosing these failures requires instance-level feedback that answers where a defect occurs, what type it is, why it is defective, and its importance to overall image quality.
arXiv:2610.00994v1 Announce Type: new Abstract: Existing synthetic image evaluators typically provide only a scalar quality score and do not identify the image regions that support it. We introduce V...
arXiv:2608.20713v1 Announce Type: new Abstract: Generative AI can now produce highly realistic images, yet current models still exhibit subtle but critical defects that undermine their reliability. W...
arXiv:2606. 07953v1 Announce Type: new Abstract: Large-scale Visual-Language Models (LVLMs) have achieved remarkable success in natural visual tasks, yet their application to industrial defect detection remains challenging due to two fundamental limitations: (i) the scarcity of large-scale industrial datasets that cover diverse defect categories across multiple domains, and (ii) the reliance on manual prompts (points, boxes, masks) that introduce subjective noise and lack text-visual interaction for fine-grained understanding.
arXiv:2609.37576v1 Announce Type: new Abstract: With the rapid advancement of text-to-image (T2I) generation, robust evaluation becomes critical yet challenging, as traditional metrics fail to captur...
UniDG introduces a unified defect generation framework that addresses the scarcity of abnormal samples in anomaly detection. By creating a large dataset of 300K normal‑abnormal‑mask‑caption quadruplets and formulating defect synthesis as Defect‑Context Editing, the model extracts reference defect context, organizes inputs in a diptych format, and fuses multimodal conditions via MM‑DiT attention. A two‑stage training strategy—Diversity‑SFT for transferable defect priors and optional Consistency‑RFT for reference adherence—enables UniDG to outperform prior few‑shot anomaly generation and editing baselines in both synthesis quality and downstream anomaly detection tasks without per‑category fine‑tuning.
Vision2Code is a new benchmark for image-to-code generation that covers 15 domains and 539 test examples without relying on reference source code. It evaluates generated programs by executing them and comparing rendered outputs to the original images using domain‑specific rubrics, yielding scores that correlate better with human judgments than generic metrics. The study shows domain variability in model performance and demonstrates that the scoring method can improve fine‑tuning of models like Qwen3.5‑9B and Phi‑4‑MM via rejection sampling.
arXiv:2604. 26633v2 Announce Type: replace-cross Abstract: Industrial surface defect inspection suffers from a fundamental data bottleneck: defects are rare, annotations require expert knowledge, and collecting balanced training sets is slow and costly.
arXiv:2608.29783v1 Announce Type: new Abstract: Industrial anomaly detection is a critical component of modern manufacturing. Most traditional unsupervised methods rely on modelling normal feature di...
arXiv:2607. 10826v1 Announce Type: cross Abstract: Automated evaluation is essential for scaling generative 3D systems, where exhaustive human review is costly and slow.
arXiv:2607. 15216v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) often introduce errors when generating image captions, resulting in misaligned image-text pairs.
The paper introduces WeGenEditBench, a benchmark with 2,740 evaluation instances and 148 task types for image editing, focusing on local failure detection and prioritization for model improvement. It also presents WeGenEvoStudio, a multi‑agent harness that supports recursive self‑improvement by diagnosing failures, constructing retrieval‑grounded data, and adapting models. Experiments show that models such as GPT‑Image‑2 and Seedream‑5.0‑Pro excel in single‑image and text‑intensive editing, and evolution experiments demonstrate significant targeted gains on selected benchmarks.