Saliency-guided object candidates based on gestalt principles

We present a new method for generating general object candidates for cluttered RGB-D scenes. Starting from an over-segmentation of the image, we build a graph representation and define an object candidate as a subgraph that has maximal internal similarity as well as minimal external similarity. These candidates are created by successively adding segments to a seed segment in a saliency-guided way. Finally, the resulting object candidates are ranked based on Gestalt principles. We show that the proposed algorithm clearly outperforms three other recent methods for object discovery on the challenging Kitchen dataset.