Original title: 3D Neural Cellular Automata
Translated title: 3D Neural Cellular Automata
Authors: Repčík, Michal ; Husa, Jakub (referee) ; Fritz, Karel (advisor)
Document type: Bachelor's theses
Year: 2026
Language: eng
Publisher: Vysoké učení technické v Brně. Fakulta informačních technologií
Abstract: [eng] [cze]
Táto bakalárska práca predstavuje modulárny framework pre 3D neurálne celulárne automaty implementovaný v Pythone a PyTorch. Riešenie pozostáva zo samostatného jadra so simuláciou a tréningovou pipeline, z TCP servera sprístupňujúceho tréning vzdialenému klientovi a z doplnku do Blenderu pre voxelizáciu cieľových 3D objektov a živé vykresľovanie rastu vo viewporte. This thesis presents a modular 3D neural cellular automata implementation in Python and PyTorch. The project includes the simulation core, a training runner, a network server for remote control, and a Blender add-on for live visualization. The work focuses on reproducibility, voxel I/O, and practical use during training and observation of volumetric growth.
Keywords: 3D voxelové modelovanie; Blender add-on; interaktívna vizualizácia; metamorfogenéza; morfogenéza; neurálne celulárne automaty; podmienené generovanie; PyTorch; TCP server; volumetrické generovanie; voxelizácia; 3D voxel modelling; Blender add-on; conditional generation; interactive visualisation; metamorphogenesis; morphogenesis; neural cellular automata; PyTorch; TCP server; volumetric generation; voxelisation

Institution: Brno University of Technology (web)
Document availability information: Fulltext is available in the Brno University of Technology Digital Library.
Original record: http://hdl.handle.net/11012/259294

Permalink: http://www.nusl.cz/ntk/nusl-776619


The record appears in these collections:
Universities and colleges > Public universities > Brno University of Technology
Academic theses (ETDs) > Bachelor's theses