# Superpixel Segmentation using Dynamic and Iterative Spanning Forest

arXiv: https://arxiv.org/abs/2007.04257 · HTML: https://mlsanity.com/paper/2007.04257/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2020.

## Built on by (most cited first, 5 of 5)

- [A comprehensive review and new taxonomy on superpixel segmentation](https://mlsanity.com/paper/2409.19179/) (2024)
- [Efficient Multiscale Object-based Superpixel Framework](https://mlsanity.com/paper/2204.03533/) (2022)
- [Improving Scene Graph Generation with Superpixel-Based Interaction Learning](https://mlsanity.com/paper/2308.02339/) (2023)
- [How to Identify Good Superpixels for Deforestation Detection on Tropical Rainforests](https://mlsanity.com/paper/2409.04330/) (2024)
- [Exploring Superpixel Segmentation Methods in the Context of Citizen Science and Deforestation Detection](https://mlsanity.com/paper/2411.17922/) (2024)

## Abstract (arXiv)

As constituent parts of image objects, superpixels can improve several higher-level operations. However, image segmentation methods might have their accuracy seriously compromised for reduced numbers of superpixels. We have investigated a solution based on the Iterative Spanning Forest (ISF) framework. In this work, we present Dynamic ISF (DISF) -- a method based on the following steps. (a) It starts from an image graph and a seed set with considerably more pixels than the desired number of superpixels. (b) The seeds compete among themselves, and each seed conquers its most closely connected pixels, resulting in an image partition (spanning forest) with connected superpixels. In step (c), DISF assigns relevance values to seeds based on superpixel analysis and removes the most irrelevant ones. Steps (b) and (c) are repeated until the desired number of superpixels is reached. DISF has the chance to reconstruct relevant edges after each iteration, when compared to region merging algorithms. As compared to other seed-based superpixel methods, DISF is more likely to find relevant seeds. It also introduces dynamic arc-weight estimation in the ISF framework for more effective superpixel delineation, and we demonstrate all results on three datasets with distinct object properties.