Depth-adaptive superpixels

We propose a novel oversegmentation technique for RGB-D images. The visible surface of the 3D geometry is partitioned into uniformly distributed and equally sized planar patches. This results in a classic over-segmentation of pixels into depth-adaptive superpixels which correctly reflect deformation through perspective projection. The advantages of depth-adaptive superpixels (DASP) are demonstrated by using spectral graph theory to create image segmentations in near realtime. Our algorithms outperform state-of-the-art oversegmentation and image segmentation algorithms both in quality and runtime.