{"ID":2840850,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.13970","arxiv_id":"2511.13970","title":"Scene Graph-Guided Generative AI Framework for Synthesizing and Evaluating Industrial Hazard Scenarios","abstract":"Training vision models to detect workplace hazards accurately requires realistic images of unsafe conditions that could lead to accidents. However, acquiring such datasets is difficult because capturing accident-triggering scenarios as they occur is nearly impossible. To overcome this limitation, this study presents a novel scene graph-guided generative AI framework that synthesizes photorealistic images of hazardous scenarios grounded in historical Occupational Safety and Health Administration (OSHA) accident reports. OSHA narratives are analyzed using GPT-4o to extract structured hazard reasoning, which is converted into object-level scene graphs capturing spatial and contextual relationships essential for understanding risk. These graphs guide a text-to-image diffusion model to generate compositionally accurate hazard scenes. To evaluate the realism and semantic fidelity of the generated data, a visual question answering (VQA) framework is introduced. Across four state-of-the-art generative models, the proposed VQA Graph Score outperforms CLIP and BLIP metrics based on entropy-based validation, confirming its higher discriminative sensitivity.","short_abstract":"Training vision models to detect workplace hazards accurately requires realistic images of unsafe conditions that could lead to accidents. However, acquiring such datasets is difficult because capturing accident-triggering scenarios as they occur is nearly impossible. To overcome this limitation, this study presents a...","url_abs":"https://arxiv.org/abs/2511.13970","url_pdf":"https://arxiv.org/pdf/2511.13970v1","authors":"[\"Sanjay Acharjee\",\"Abir Khan Ratul\",\"Diego Patino\",\"Md Nazmus Sakib\"]","published":"2025-11-17T22:58:27Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}