Generating real-time detailed ground visualisations from sparse aerial point clouds
This addresses the cost and accuracy issues in generating detailed ground visualizations for domains such as simulation and gaming, though it appears incremental as it builds on existing scanning and rendering techniques.
The paper tackles the problem of creating realistic outdoor 3D ground visualizations from sparse aerial point clouds, which is typically expensive and inaccurate when done manually by artists, and proposes an automated method to amplify scanned data and render real-time animated 3D content for applications like training and video games.
Building realistic wide scale outdoor 3D content with sufficient visual quality to observe at walking eye level or from driven vehicles is often carried out by large teams of artists skilled in modelling, texturing, material shading and lighting, which typically leads to both prohibitive costs and reduced accuracy honoring the variety of real world ground truth landscapes. In our proposed method, we define a process to automatically amplify real-world scanned data and render real-time in animated 3D to explore at close range with high quality for training, simulation, video game and visualisation applications.