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...
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.