# Image segmentation via Cellular Automata

arXiv: https://arxiv.org/abs/2008.04965 · HTML: https://mlsanity.com/paper/2008.04965/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2020.

## Built on by (most cited first, 15 of 15)

- [Attention-based Neural Cellular Automata](https://mlsanity.com/paper/2211.01233/) (2022)
- [Med-NCA: Robust and Lightweight Segmentation with Neural Cellular Automata](https://mlsanity.com/paper/2302.03473/) (2023)
- [M3D-NCA: Robust 3D Segmentation with Built-in Quality Control](https://mlsanity.com/paper/2309.02954/) (2023)
- [Generative Adversarial Neural Cellular Automata](https://mlsanity.com/paper/2108.04328/) (2021)
- [Differentiable Logic Cellular Automata: From Game of Life to Pattern Generation](https://mlsanity.com/paper/2506.04912/) (2025)
- [NoiseNCA: Noisy Seed Improves Spatio-Temporal Continuity of Neural Cellular Automata](https://mlsanity.com/paper/2404.06279/) (2024)
- [Neural Cellular Automata: From Cells to Pixels](https://mlsanity.com/paper/2506.22899/) (2025)
- [AdaNCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer](https://mlsanity.com/paper/2406.08298/) (2024)
- [NCA-Morph: Medical Image Registration with Neural Cellular Automata](https://mlsanity.com/paper/2410.22265/) (2024)
- [OctreeNCA: Single-Pass 184 MP Segmentation on Consumer Hardware](https://mlsanity.com/paper/2508.06993/) (2025)
- [A New Kind of Network? Review and Reference Implementation of Neural Cellular Automata](https://mlsanity.com/paper/2604.24990/) (2026)
- [Missing Data Imputation using Neural Cellular Automata](https://mlsanity.com/paper/2509.00651/) (2025)
- [Applications of Neural Cellular Automata: State of the Art, Challenges and Opportunities](https://mlsanity.com/paper/2609.24595/) (2026)
- [Reasoning with Neural Cellular Automata](https://mlsanity.com/paper/2609.36126/) (2026)
- [2D Spatial Reasoning with Adaptive Neural Cellular Automata](https://mlsanity.com/paper/2610.08518/) (2026)

## Abstract (arXiv)

In this paper, we propose a new approach for building cellular automata to solve real-world segmentation problems. We design and train a cellular automaton that can successfully segment high-resolution images. We consider a colony that densely inhabits the pixel grid, and all cells are governed by a randomized update that uses the current state, the color, and the state of the 3× 3 neighborhood. The space of possible rules is defined by a small neural network. The update rule is applied repeatedly in parallel to a large random subset of cells and after convergence is used to produce segmentation masks that are then back-propagated to learn the optimal update rules using standard gradient descent methods. We demonstrate that such models can be learned efficiently with only limited trajectory length and that they show remarkable ability to organize the information to produce a globally consistent segmentation result, using only local information exchange. From a practical perspective, our approach allows us to build very efficient models -- our smallest automaton uses less than 10,000 parameters to solve complex segmentation tasks.