Automatic infrastructure visual inspection using Unmanned Aerial Vehicles (UAVs) enhances efficiency and safety. However, existing approaches lack context-aware path planning capabilities, often leading to redundant inspections without focus. To address this limitation, this study introduces a novel infrastructure inspection paradigm that integrates 3D coverage path planning (3D-CPP), real-time data interpretation, and inspection information management, to generate and refine 3D-CPP progressively based on recorded information and real-time observation. The proposed paradigm consists of two main components. First, a graph-based information management system named Semantic-PolygonGraph is developed to incorporate static information from Industry Foundation Classes (IFC) alongside dynamically accumulated inspection data. Second, leveraging this structured representation, a progressive 3D-CPP method is proposed to generates an adaptive inspection path that dynamically refines itself based on task requirements, historical records, and real-time observations, prioritizing regions exhibiting superficial damage. To evaluate the effectiveness of the proposed paradigm, this study introduces a data quality assessment metric to quantify the trade-off between inspection cost and data quality. Simulated case studies demonstrate that the proposed approach improves data quality with limited increase of inspection costs, highlighting its potential for long-term infrastructure maintenance.