Terrain Diffusion Network: Climatic-Aware Terrain Generation with Geological Sketch Guidance

TL;DR

This paper introduces a novel diffusion-based terrain generation method that incorporates user guidance and multi-level denoising to produce realistic, controllable landscapes with detailed features influenced by climatic patterns.

Contribution

The paper proposes the terrain diffusion network (TDN), a new multi-level denoising approach with terrain and sketch latent spaces, enhancing controllability and realism in terrain synthesis.

Findings

Achieves state-of-the-art performance on NASA Topology Images dataset.

Effectively incorporates user guidance for controllable terrain generation.

Produces more realistic terrains with detailed features and climatic pattern influence.

Abstract

Sketch-based terrain generation seeks to create realistic landscapes for virtual environments in various applications such as computer games, animation and virtual reality. Recently, deep learning based terrain generation has emerged, notably the ones based on generative adversarial networks (GAN). However, these methods often struggle to fulfill the requirements of flexible user control and maintain generative diversity for realistic terrain. Therefore, we propose a novel diffusion-based method, namely terrain diffusion network (TDN), which actively incorporates user guidance for enhanced controllability, taking into account terrain features like rivers, ridges, basins, and peaks. Instead of adhering to a conventional monolithic denoising process, which often compromises the fidelity of terrain details or the alignment with user control, a multi-level denoising scheme is proposed to generate more realistic terrains by taking into account fine-grained details, particularly those related to climatic patterns influenced by erosion and tectonic activities. Specifically, three terrain synthesisers are designed for structural, intermediate, and fine-grained level denoising purposes, which allow each synthesiser concentrate on a distinct terrain aspect. Moreover, to maximise the efficiency of our TDN, we further introduce terrain and sketch latent spaces for the synthesizers with pre-trained terrain autoencoders. Comprehensive experiments on a new dataset constructed from NASA Topology Images clearly demonstrate the effectiveness of our proposed method, achieving the state-of-the-art performance. Our code and dataset will be publicly available.