# H-SPAM: Hierarchical Superpixel Anything Model

arXiv: https://arxiv.org/abs/2604.11218 · HTML: https://mlsanity.com/paper/2604.11218/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Fast Segment Anything](https://mlsanity.com/paper/2306.12156/) (2023)
- [Superpixel Sampling Networks](https://mlsanity.com/paper/1807.10174/) (2018)
- [SEEDS: Superpixels Extracted via Energy-Driven Sampling](https://mlsanity.com/paper/1309.3848/) (2013)
- [Superpixel Segmentation with Fully Convolutional Networks](https://mlsanity.com/paper/2003.12929/) (2020)
- [Superpixels: An Evaluation of the State-of-the-Art](https://mlsanity.com/paper/1612.01601/) (2016)
- [StructNeRF: Neural Radiance Fields for Indoor Scenes with Structural Hints](https://mlsanity.com/paper/2209.05277/) (2022)
- [Learning Hierarchical Image Segmentation For Recognition and By Recognition](https://mlsanity.com/paper/2210.00314/) (2022)
- [Superpixel Hierarchy](https://mlsanity.com/paper/1605.06325/) (2016)
- [SPFormer: Enhancing Vision Transformer with Superpixel Representation](https://mlsanity.com/paper/2401.02931/) (2024)
- [HERS Superpixels: Deep Affinity Learning for Hierarchical Entropy Rate Segmentation](https://mlsanity.com/paper/2106.03755/) (2021)
- [Superpixel-informed Implicit Neural Representation for Multi-Dimensional Data](https://mlsanity.com/paper/2411.11356/) (2024)
- [Evaluation Framework of Superpixel Methods with a Global Regularity Measure](https://mlsanity.com/paper/1903.07162/) (2019)
- [Learning Invariant Inter-pixel Correlations for Superpixel Generation](https://mlsanity.com/paper/2402.18201/) (2024)
- [Superpixel Anything: A general object-based framework for accurate yet regular superpixel segmentation](https://mlsanity.com/paper/2509.12791/) (2025)
- [Superpixel Segmentation: A Long-Lasting Ill-Posed Problem](https://mlsanity.com/paper/2411.06478/) (2024)
- [Hierarchical Superpixel Segmentation via Structural Information Theory](https://mlsanity.com/paper/2501.07069/) (2025)

## Abstract (arXiv)

Superpixels offer a compact image representation by grouping pixels into coherent regions. Recent methods have reached a plateau in terms of segmentation accuracy by generating noisy superpixel shapes. Moreover, most existing approaches produce a single fixed-scale partition that limits their use in vision pipelines that would benefit multi-scale representations. In this work, we introduce H-SPAM (Hierarchical Superpixel Anything Model), a unified framework for generating accurate, regular, and perfectly nested hierarchical superpixels. Starting from a fine partition, guided by deep features and external object priors, H-SPAM constructs the hierarchy through a two-phase region merging process that first preserves object consistency and then allows controlled inter-object grouping. The hierarchy can also be modulated using visual attention maps or user input to preserve important regions longer in the hierarchy. Experiments on standard benchmarks show that H-SPAM strongly outperforms existing hierarchical methods in both accuracy and regularity, while performing on par with most recent state-of-the-art non-hierarchical methods. Code and pretrained models are available: https://github.com/waldo-j/hspam.