Achanta, RadhakrishnaSüsstrunk, Sabine2017-04-062017-04-062017-04-06201710.1109/Cvpr.2017.520https://infoscience.epfl.ch/handle/20.500.14299/136422WOS:000418371404104We present an improved version of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation. Unlike SLIC, our algorithm is non-iterative, enforces connectivity from the start, requires lesser memory, and is faster. Relying on the superpixel boundaries obtained using our algorithm, we also present a polygonal partitioning algorithm. We demonstrate that our superpixels as well as the polygonal partitioning are superior to the respective state-of-the-art algorithms on quantitative benchmarks.SLICsuperpixelsCIELAB color spacepolygonal partitioningtext::conference output::conference proceedings::conference paper