# Growing 3D Artefacts and Functional Machines with Neural Cellular Automata

arXiv: https://arxiv.org/abs/2103.08737 · HTML: https://mlsanity.com/paper/2103.08737/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 22 references that are in the map.
- First posted on arXiv 15 Mar 2021.

## Builds on (most cited first, 7 of 7)

- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards](https://mlsanity.com/paper/1707.08817/) (2017)
- [EvoCraft: A New Challenge for Open-Endedness](https://mlsanity.com/paper/2012.04751/) (2020)
- [Learning to Generate 3D Shapes with Generative Cellular Automata](https://mlsanity.com/paper/2103.04130/) (2021)
- [Regenerating Soft Robots through Neural Cellular Automata](https://mlsanity.com/paper/2102.02579/) (2021)
- [Neural Cellular Automata Manifold](https://mlsanity.com/paper/2006.12155/) (2020)

## Built on by (most cited first, 30 of 38)

- [Illuminating Diverse Neural Cellular Automata for Level Generation](https://mlsanity.com/paper/2109.05489/) (2021)
- [HyperNCA: Growing Developmental Networks with Neural Cellular Automata](https://mlsanity.com/paper/2204.11674/) (2022)
- [Towards Self-Assembling Artificial Neural Networks through Neural Developmental Programs](https://mlsanity.com/paper/2307.08197/) (2023)
- [DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft](https://mlsanity.com/paper/2404.15538/) (2024)
- [World-GAN: a Generative Model for Minecraft Worlds](https://mlsanity.com/paper/2106.10155/) (2021)
- [ARC-NCA: Towards Developmental Solutions to the Abstraction and Reasoning Corpus](https://mlsanity.com/paper/2505.08778/) (2025)
- [Goal-Guided Neural Cellular Automata: Learning to Control Self-Organising Systems](https://mlsanity.com/paper/2205.06806/) (2022)
- [Open-Ended Evolution for Minecraft Building Generation](https://mlsanity.com/paper/2209.03108/) (2022)
- [E(n)-equivariant Graph Neural Cellular Automata](https://mlsanity.com/paper/2301.10497/) (2023)
- [Arbitrarily Scalable Environment Generators via Neural Cellular Automata](https://mlsanity.com/paper/2310.18622/) (2023)
- [Neural cellular automata: applications to biology and beyond classical AI](https://mlsanity.com/paper/2509.11131/) (2025)
- [From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models](https://mlsanity.com/paper/2407.09502/) (2024)
- [Physical Neural Cellular Automata for 2D Shape Classification](https://mlsanity.com/paper/2203.07548/) (2022)
- [Growing Steerable Neural Cellular Automata](https://mlsanity.com/paper/2302.10197/) (2023)
- [Neural Cellular Automata: From Cells to Pixels](https://mlsanity.com/paper/2506.22899/) (2025)
- [A Unified Substrate for Body-Brain Co-evolution](https://mlsanity.com/paper/2203.12066/) (2022)
- [Severe Damage Recovery in Evolving Soft Robots through Differentiable Programming](https://mlsanity.com/paper/2206.06674/) (2022)
- [Evolving Flying Machines in Minecraft Using Quality Diversity](https://mlsanity.com/paper/2302.00782/) (2023)
- [Latent Neural Cellular Automata for Resource-Efficient Image Restoration](https://mlsanity.com/paper/2403.15525/) (2024)
- [Collective control of modular soft robots via embodied Spiking Neural Cellular Automata](https://mlsanity.com/paper/2204.02099/) (2022)
- [A Review of Deep Learning-Powered Mesh Reconstruction Methods](https://mlsanity.com/paper/2303.02879/) (2023)
- [Empowered Neural Cellular Automata](https://mlsanity.com/paper/2205.06771/) (2022)
- [Collective Intelligence for 2D Push Manipulations with Mobile Robots](https://mlsanity.com/paper/2211.15136/) (2022)
- [Scaffold Diffusion: Sparse Multi-Category Voxel Structure Generation with Discrete Diffusion](https://mlsanity.com/paper/2509.00062/) (2025)
- [Quality Diversity in the Amorphous Fortress (QD-AF): Evolving for Complexity in 0-Player Games](https://mlsanity.com/paper/2312.02231/) (2023)
- [Emergent Dynamics in Neural Cellular Automata](https://mlsanity.com/paper/2404.06406/) (2024)
- [Remapping and navigation of an embedding space via error minimization: a fundamental organizational principle of cognition in natural and artificial systems](https://mlsanity.com/paper/2601.14096/) (2026)
- [On the Emergence of Syntax by Means of Local Interaction](https://mlsanity.com/paper/2604.17857/) (2026)
- [Neural Cellular Automata Learn General Features in their Hidden Channels](https://mlsanity.com/paper/2609.21870/) (2026)
- [Future Research Avenues for Artificial Intelligence in Digital Gaming: An Exploratory Report](https://mlsanity.com/paper/2412.14085/) (2024)

## Abstract (arXiv)

Neural Cellular Automata (NCAs) have been proven effective in simulating morphogenetic processes, the continuous construction of complex structures from very few starting cells. Recent developments in NCAs lie in the 2D domain, namely reconstructing target images from a single pixel or infinitely growing 2D textures. In this work, we propose an extension of NCAs to 3D, utilizing 3D convolutions in the proposed neural network architecture. Minecraft is selected as the environment for our automaton since it allows the generation of both static structures and moving machines. We show that despite their simplicity, NCAs are capable of growing complex entities such as castles, apartment blocks, and trees, some of which are composed of over 3,000 blocks. Additionally, when trained for regeneration, the system is able to regrow parts of simple functional machines, significantly expanding the capabilities of simulated morphogenetic systems. The code for the experiment in this paper can be found at: https://github.com/real-itu/3d-artefacts-nca.