Saved in:
Bibliographic Details
Main Authors: Catrina, Mirela-Magdalena, Plajer, Ioana Cristina, Băicoianu, Alexandra
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.13630
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917491655049216
author Catrina, Mirela-Magdalena
Plajer, Ioana Cristina
Băicoianu, Alexandra
author_facet Catrina, Mirela-Magdalena
Plajer, Ioana Cristina
Băicoianu, Alexandra
contents This study significantly advances multi-texture synthesis using Neural Cellular Automata (NCAs) by introducing a novel training methodology that enables robust self-regeneration of textures in damaged regions. This inherent healing mechanism, essential for dynamic and adaptive systems, extends beyond traditional computer graphics applications, highlighting the fundamental self-organizing properties of NCAs. Furthermore, we present a versatile grafting technique, enabling the seamless combination of distinct textures. This is achieved efficiently during the inference phase, without requiring specialized retraining, through precise initialization of the NCA's genome channels. Our findings demonstrate the generation of high-quality, complex textures with fluid transitions, showcasing a powerful and efficient paradigm for dynamic texture composition and self-repair in autonomous systems.
format Preprint
id arxiv_https___arxiv_org_abs_2605_13630
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Texture Regenerating and Grafting Using Genome-Driven Neural Cellular Automata
Catrina, Mirela-Magdalena
Plajer, Ioana Cristina
Băicoianu, Alexandra
Neural and Evolutionary Computing
This study significantly advances multi-texture synthesis using Neural Cellular Automata (NCAs) by introducing a novel training methodology that enables robust self-regeneration of textures in damaged regions. This inherent healing mechanism, essential for dynamic and adaptive systems, extends beyond traditional computer graphics applications, highlighting the fundamental self-organizing properties of NCAs. Furthermore, we present a versatile grafting technique, enabling the seamless combination of distinct textures. This is achieved efficiently during the inference phase, without requiring specialized retraining, through precise initialization of the NCA's genome channels. Our findings demonstrate the generation of high-quality, complex textures with fluid transitions, showcasing a powerful and efficient paradigm for dynamic texture composition and self-repair in autonomous systems.
title Texture Regenerating and Grafting Using Genome-Driven Neural Cellular Automata
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2605.13630