3D Building Generation in Minecraft via Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Shiying, Huang, Zengrong, Hu, Chengpeng, Liu, Jialin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916285156163584
author Hu, Shiying
Huang, Zengrong
Hu, Chengpeng
Liu, Jialin
author_facet Hu, Shiying
Huang, Zengrong
Hu, Chengpeng
Liu, Jialin
contents Recently, procedural content generation has exhibited considerable advancements in the domain of 2D game level generation such as Super Mario Bros. and Sokoban through large language models (LLMs). To further validate the capabilities of LLMs, this paper explores how LLMs contribute to the generation of 3D buildings in a sandbox game, Minecraft. We propose a Text to Building in Minecraft (T2BM) model, which involves refining prompts, decoding interlayer representation and repairing. Facade, indoor scene and functional blocks like doors are supported in the generation. Experiments are conducted to evaluate the completeness and satisfaction of buildings generated via LLMs. It shows that LLMs hold significant potential for 3D building generation. Given appropriate prompts, LLMs can generate correct buildings in Minecraft with complete structures and incorporate specific building blocks such as windows and beds, meeting the specified requirements of human users.
format Preprint
id arxiv_https___arxiv_org_abs_2406_08751
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle 3D Building Generation in Minecraft via Large Language Models
Hu, Shiying
Huang, Zengrong
Hu, Chengpeng
Liu, Jialin
Artificial Intelligence
Recently, procedural content generation has exhibited considerable advancements in the domain of 2D game level generation such as Super Mario Bros. and Sokoban through large language models (LLMs). To further validate the capabilities of LLMs, this paper explores how LLMs contribute to the generation of 3D buildings in a sandbox game, Minecraft. We propose a Text to Building in Minecraft (T2BM) model, which involves refining prompts, decoding interlayer representation and repairing. Facade, indoor scene and functional blocks like doors are supported in the generation. Experiments are conducted to evaluate the completeness and satisfaction of buildings generated via LLMs. It shows that LLMs hold significant potential for 3D building generation. Given appropriate prompts, LLMs can generate correct buildings in Minecraft with complete structures and incorporate specific building blocks such as windows and beds, meeting the specified requirements of human users.
title 3D Building Generation in Minecraft via Large Language Models
topic Artificial Intelligence
url https://arxiv.org/abs/2406.08751