发表机构
University of Engineering and Technology, Vietnam National University（越南国家大学工程技术大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对反射表面检测的视角局限问题，提出多视角检测框架，通过语义-显著性交叉验证提升缺陷检测的AP₅₀与跨视角证据召回率。
AI 中文摘要
智能手机盖板玻璃因反射特性，从单一固定视角检测存在挑战：缺陷可见度随观测几何和镜面反射变化，导致两个实际问题：部分视角下缺陷观测性弱，且现有视觉证据存在空间歧义。为解决这些问题，本文提出多视角检测框架，其中每个RGB观测由共享的单视角专家处理；视觉语言模型（VLM）生成类别感知的语义框，法线参考重建分支提供类别无关的显著性；将两者的空间一致性作为支持证据对语义候选进行排序，不修改其坐标也不将显著性视为真值；最终在产品层面合并证据记录，无需跨视角配准。在282张生产线图像上，语义-显著性关联通过重排序固定语义候选，使AP₅₀从52.6%提升至62.6%；在94个产品上，跨视角证据召回率R_prod@0.5从最佳单视角的75.5%提升至使用全部三个视角的88.3%。这些结果表明，语义-显著性交叉验证及额外光学观测在反射表面检测中具有互补作用。
英文摘要
Reflective smartphone cover glass is challenging to inspect from a single fixed viewpoint because defect visibility varies with viewing geometry and specular reflections. This gives rise to two practical challenges: defects may be weakly observable from certain viewpoints, while the available visual evidence may remain spatially ambiguous. To address these issues, we propose a multi-view inspection framework in which each RGB observation is processed by a shared per-view expert. A vision-language model (VLM) produces class-aware semantic boxes, while a normal-reference reconstruction branch provides class-agnostic saliency. Their spatial agreement is used as supporting evidence to rank semantic proposals without modifying their coordinates or treating saliency as ground truth. The resulting evidence records are combined at product level without cross-view registration. On 282 production-line images, semantic-saliency association improves $AP_{50}$ from 52.6% to 62.6% by re-ranking fixed semantic proposals. Across 94 products, cross-view evidence recall $R_{\rm prod}@0.5$ increases from 75.5% for the best single view to 88.3% using all three views. These results support the complementary roles of semantic-saliency cross-verification and additional optical observations in reflective-surface inspection.
CommentsSubmitted to RIVF 2026
