Eikonal-based region growing for efficient clustering

We describe an Eikonal-based algorithm for computing dense oversegmentation of an image, often called superpixels. This oversegmentation respect local image boundaries while limiting undersegmentation. The proposed algorithm relies on a region growing scheme, where the potential map used is not xed and evolves during the di usion. Re nement steps are also proposed to enhance at low cost the rst oversegmentation. Quantitative comparisons on the Berkeley dataset show good performance on traditional metrics over current state-of-the art superpixel methods.