Active Scene Capturing for Image-Based Rendering with a Light Field Setup

With image-based rendering (IBR) one can render 3D scenes from multiple images with or without geometry. Various approaches to IBR have been proposed to render the scene given a set of regularly or non-regularly pre-captured images. In this paper, we propose an algorithm to capture the images actively. Based on the images that have been taken, the system intelligently determines where to pose the next camera for best rendering performance. This results in non-uniform but optimal capturing of the scene. We also propose a local-consistency voxel coloring algorithm that can find 3D geometry for non-Lambertian scenes. The full active capturing algorithm combines the above two components and is able to render better quality images compared with traditional methods.