An analysis of 3D point cloud reconstruction from light field images

Current methodologies for the generation of 3D point cloud from real world scenes rely upon a set of 2D images capturing the scene from several points of view. Novel plenoptic cameras sample the light field crossing the main camera lens creating a light field image. The information available in a plenoptic image must be processed in order to render a view or create the depth map of the scene. This paper analyses a method for the reconstruction of 3D models. The reconstruction of the model is obtained from a single image shot. Exploiting the properties of plenoptic images, a point cloud is generated and compared with a point cloud of the same object but generated with a different plenoptic camera.