Controllable Procedural Generation of Landscapes

Jia-Hong Liu, Shao-Kui Zhang, Chuyue Zhang, Song-Hai Zhang

Abstract: Landscapes, recognized for their indispensable role in large-scale scenes, are experiencing growing demand. However, the manual modeling of such content is labor-intensive and lacks efficiency. Procedural Content Generation (PCG) techniques enable the rapid generation of diverse landscape elements. Nevertheless, ordinary users may encounter difficulties controlling these methods for desired results. In this paper, we introduce a controllable framework for procedurally generating landscapes. We integrate state-of-the-art Large Language Models (LLMs) to enhance user accessibility and control. By converting plain text inputs into parameters through LLMs, our framework allows ordinary users to generate a batch of plausible landscapes tailored to their specifications. A parameter-controlled PCG procedure is designed to leverage optimization techniques and employ rule-based refinements. It achieves harmonious layering in terrains, zoning, and roads while enabling aesthetic arrangement of vegetation and artificial elements. Extensive experiments demonstrate our framework's effectiveness in generating landscapes comparable to those crafted by experienced architects. Our framework has the potential to enhance the productivity of landscape designers significantly.

Primary Subject Area: [Experience] Art and Culture

Secondary Subject Area: [Generation] Multimedia Foundation Models, [Experience] Multimedia Applications

Relevance To Conference: This paper introduces a controllable framework for procedurally generating landscapes. Firstly, it aligns with the subject of "Art and Culture". Landscapes are indispensable artworks in real-world and virtual outdoor environments, conveying cultural and aesthetic impressions. We propose a framework that integrates a Large Language Model (LLM) and combines optimization and rule-based Procedural Content Generation (PCG) techniques. It generates plausible landscapes with harmonious layering in terrains, zoning, roads, vegetation, and artificial elements. Experiments demonstrate that landscapes generated by our framework are comparable to those designed by professional architects. Secondly, it falls under the subject of "Multimedia Foundation Models". We employ the LLM to convert the user input into parameters that govern the generation of landscapes. The LLM enables accurate adaptation to various landscape configurations and enhances user-centered control of more practical landscapes. Finally, it serves as a "Multimedia Application". Our framework enables ordinary users to generate desirable landscapes through simple text descriptions, potentially enhancing design productivity.

Submission Number: 30