DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914768138272768 |
|---|---|
| author | Earle, Sam Kokkinos, Filippos Nie, Yuhe Togelius, Julian Raileanu, Roberta |
| author_facet | Earle, Sam Kokkinos, Filippos Nie, Yuhe Togelius, Julian Raileanu, Roberta |
| contents | Procedural Content Generation (PCG) algorithms enable the automatic generation of complex and diverse artifacts. However, they don't provide high-level control over the generated content and typically require domain expertise. In contrast, text-to-3D methods allow users to specify desired characteristics in natural language, offering a high amount of flexibility and expressivity. But unlike PCG, such approaches cannot guarantee functionality, which is crucial for certain applications like game design. In this paper, we present a method for generating functional 3D artifacts from free-form text prompts in the open-world game Minecraft. Our method, DreamCraft, trains quantized Neural Radiance Fields (NeRFs) to represent artifacts that, when viewed in-game, match given text descriptions. We find that DreamCraft produces more aligned in-game artifacts than a baseline that post-processes the output of an unconstrained NeRF. Thanks to the quantized representation of the environment, functional constraints can be integrated using specialized loss terms. We show how this can be leveraged to generate 3D structures that match a target distribution or obey certain adjacency rules over the block types. DreamCraft inherits a high degree of expressivity and controllability from the NeRF, while still being able to incorporate functional constraints through domain-specific objectives. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_15538 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft Earle, Sam Kokkinos, Filippos Nie, Yuhe Togelius, Julian Raileanu, Roberta Graphics Artificial Intelligence Computation and Language Machine Learning Procedural Content Generation (PCG) algorithms enable the automatic generation of complex and diverse artifacts. However, they don't provide high-level control over the generated content and typically require domain expertise. In contrast, text-to-3D methods allow users to specify desired characteristics in natural language, offering a high amount of flexibility and expressivity. But unlike PCG, such approaches cannot guarantee functionality, which is crucial for certain applications like game design. In this paper, we present a method for generating functional 3D artifacts from free-form text prompts in the open-world game Minecraft. Our method, DreamCraft, trains quantized Neural Radiance Fields (NeRFs) to represent artifacts that, when viewed in-game, match given text descriptions. We find that DreamCraft produces more aligned in-game artifacts than a baseline that post-processes the output of an unconstrained NeRF. Thanks to the quantized representation of the environment, functional constraints can be integrated using specialized loss terms. We show how this can be leveraged to generate 3D structures that match a target distribution or obey certain adjacency rules over the block types. DreamCraft inherits a high degree of expressivity and controllability from the NeRF, while still being able to incorporate functional constraints through domain-specific objectives. |
| title | DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft |
| topic | Graphics Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2404.15538 |