Figure 1: Superpixel segmentations with approximately $600$ superpixels generated by the original implementation of SEEDS.
 P. Arbeláez, M. Maire, C. Fowlkes, J. Malik. Contour detection and hierarchical image segmentation. Transactions on Pattern Analysis and Machine Intelligence, volume 33, number 5, pages 898–916, 2011.
Van den Bergh et al. propose a superpixel algorithm called SEEDS using color histograms to refine an initial superpixel segmentation. The main goal of my bachelor thesis is the integration of depth information into SEEDS, see my bachelor thesis proposal and the slides of my introductory talk. Figure 1 shows images from the validation set of the Berkeley Segmentation Dataset  oversegmented using the original implementation of SEEDS.
Update. Thorough evaluation of both the original implementation and my implementation of SEEDS can be found in my bachelor thesis: Bachelor Thesis “Superpixel Segmentation Using Depth Information”.