arxivst stuff from arxiv that you should probably bookmark

Saliency-guided Adaptive Seeding for Supervoxel Segmentation

Abstract · Apr 13, 2017 09:43 ·

superpixels salient supervoxels saliency guided ssv superpixel vccs supervoxel seeding cs-cv

Arxiv Abstract

  • Ge Gao
  • Mikko Lauri
  • Simone Frintrop

We propose a new saliency-guided method for generating supervoxels in 3D space. Rather than using an evenly distributed spatial seeding procedure, our method uses visual saliency to guide the process of supervoxel generation. This results in densely distributed, small, and precise supervoxels in salient regions which often contain objects, and larger supervoxels in less salient regions that often correspond to background. Our approach largely improves the quality of the resulting supervoxel segmentation in terms of boundary recall and under-segmentation error on publicly available benchmarks.

Read the paper (pdf) »