THE USE OF GENERATIVE NEURAL NETWORKS IN PROCEDURAL MODELING OF GAME WORLDS

The article explores the application of generative neural networks in procedural modeling of game worlds, enabling the automation of game content creation, including levels, scenarios, 3D objects, textures, and NPC behavior.The study aims to analyze the role of generative neural networks in shaping game environments, identify key types of generated content, and examine modern algorithms and models that enhance procedural generation.The study employed general scientific methods of cognition based on analysis, synthesis, comparison of scientific literature, and expert publications.The findings indicate that generative neural networks serve as a crucial tool in procedural content creation.They facilitate the efficient automation of game design development, significantly reducing the time required to construct game environments.The study identified key types of generated content, including graphical elements, audio components, spatial structures, interaction systems, storylines, balancing mechanics, and other supplementary data.The analysis revealed that different neural network architectures are applied to generate various aspects of the gaming experience.Specifically, convolutional neural networks are used for processing images and textures; recurrent neural networks generate scripts and event sequences; autoencoders compress and optimize data; while generative adversarial networks (GANs) create realistic objects and structures.Advanced technologies enhance 3D visualization and automated game object generation, contributing to the development of more realistic and logically structured gaming environments.The study suggests that future developments in neural networks will focus on integrating different generation methods and improving training datasets to enhance content quality.The practical significance of the research lies in its potential to reduce video game development costs while increasing the level of detail and realism in virtual worlds, opening new prospects for the gaming industry.

Authors

Institutions

Publication Details

Journal
Věda a perspektivy
Published
2025-05-02
DOI
https://doi.org/10.52058/2695-1592-2025-4(47)-239-246
Primary Topic
Advanced Research in Systems and Signal Processing
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

THE USE OF GENERATIVE NEURAL NETWORKS IN PROCEDURAL MODELING OF GAME WORLDS

Yuliia Yermolaieva
Věda a perspektivy
Advanced Research in Systems and Signal Processing
article

THE USE OF GENERATIVE NEURAL NETWORKS IN PROCEDURAL MODELING OF GAME WORLDS

Yuliia Yermolaieva
article en

Abstract

The article explores the application of generative neural networks in procedural modeling of game worlds, enabling the automation of game content creation, including levels, scenarios, 3D objects, textures, and NPC behavior.The study aims to analyze the role of generative neural networks in shaping game environments, identify key types of generated content, and examine modern algorithms and models that enhance procedural generation.The study employed general scientific methods of cognition based on analysis, synthesis, comparison of scientific literature, and expert publications.The findings indicate that generative neural networks serve as a crucial tool in procedural content creation.They facilitate the efficient automation of game design development, significantly reducing the time required to construct game environments.The study identified key types of generated content, including graphical elements, audio components, spatial structures, interaction systems, storylines, balancing mechanics, and other supplementary data.The analysis revealed that different neural network architectures are applied to generate various aspects of the gaming experience.Specifically, convolutional neural networks are used for processing images and textures; recurrent neural networks generate scripts and event sequences; autoencoders compress and optimize data; while generative adversarial networks (GANs) create realistic objects and structures.Advanced technologies enhance 3D visualization and automated game object generation, contributing to the development of more realistic and logically structured gaming environments.The study suggests that future developments in neural networks will focus on integrating different generation methods and improving training datasets to enhance content quality.The practical significance of the research lies in its potential to reduce video game development costs while increasing the level of detail and realism in virtual worlds, opening new prospects for the gaming industry.

Věda a perspektivy(4(47))
Interactive Research and Development (PK)
Openalex Percentile: Top 90%
Advanced Research in Systems and Signal Processing
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

THE USE OF GENERATIVE NEURAL NETWORKS IN PROCEDURAL MODELING OF GAME WORLDS — Yuliia Yermolaieva · Věda a perspektivy (2025) | TGRS Research Map | TGRS