3D reconstruction from plenoptic image

Novel plenoptic cameras sample the light field crossing the main camera lens. The information available in a plenoptic image can be processed, in order to create the depth map of the scene, from a single camera shot. In this paper a novel algorithm, for the reconstruction of 3D point cloud of the scene from a single plenoptic image, taken with a consumer plenoptic camera, is proposed. Experimental analysis is conducted on several test images, and results are compared with state of the art methodology. The results are very promising, as the quality of the 3D point cloud from plenoptic image, is comparable with the quality obtained with current methodologies, that necessitates of more than one image.