Procedural terrain generation with style transfer

TL;DR

This paper presents a novel terrain generation method combining procedural noise and neural style transfer, producing diverse, realistic landscapes with low computational cost and high versatility for designers.

Contribution

It introduces an innovative fusion of procedural noise and neural style transfer for terrain generation, offering a more versatile and efficient alternative to existing models.

Findings

Produces terrains closely resembling real-world landscapes

Achieves lower hardware requirements than traditional methods

Demonstrates superior terrain morphology replication

Abstract

In this study we introduce a new technique for the generation of terrain maps, exploiting a combination of procedural generation and Neural Style Transfer. We consider our approach to be a viable alternative to competing generative models, with our technique achieving greater versatility, lower hardware requirements and greater integration in the creative process of designers and developers. Our method involves generating procedural noise maps using either multi-layered smoothed Gaussian noise or the Perlin algorithm. We then employ an enhanced Neural Style transfer technique, drawing style from real-world height maps. This fusion of algorithmic generation and neural processing holds the potential to produce terrains that are not only diverse but also closely aligned with the morphological characteristics of real-world landscapes, with our process yielding consistent terrain structures with low computational cost and offering the capability to create customized maps. Numerical evaluations further validate our model's enhanced ability to accurately replicate terrain morphology, surpassing traditional procedural methods.