“…Semantic segmentation is the task of assigning a class label to each pixel in an image and is one of the fundamental problems in computer vision. Semantic segmentation has also been used to integrate higher-level scene understanding into other computer vision problems, e.g., dense 3D reconstruction [6,13,14,23,28,31,55,56,61], SLAM [7,35] and Structure-from-Motion [3], 3D model alignment [15,16,73], and location recognition [1,42,60].…”