# Saliency-guided Adaptive Seeding for Supervoxel Segmentation

arXiv: https://arxiv.org/abs/1704.04054 · HTML: https://mlsanity.com/paper/1704.04054/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2017.

## Built on by (most cited first, 2 of 2)

- [SOS: Segment Object System for Open-World Instance Segmentation With Object Priors](https://mlsanity.com/paper/2409.14627/) (2024)
- [EZ-SP: Fast and Lightweight Superpoint-Based 3D Segmentation](https://mlsanity.com/paper/2512.00385/) (2025)

## Abstract (arXiv)

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.