Example-Based Realistic Terrain Generation

Terrain texture plays a great role on visualization in many 3D applications. Sometimes terrain texture is difficult to obtain in a desired area, thus a new approach to terrain texture generation based on satellite images is proposed to resolve this problem. We prepare a silhouette map and a satellite image for the desired terrain texture and colorize the two pictures with the same pattern according to the terrain features. Then a method of texture synthesis is adopted to generate the final terrain texture.

show abstract

“…Our method can generate discretional terrain texture through simple interaction. This is a continued work of our terrain generation [7].…”

Section: Feature Matchingmentioning

confidence: 84%

Region-Based Artificial Terrain Texture Generation

Zhao

Zhang

et al. 2007

Virtual Reality

Self Cite

View full text Add to dashboard Cite

show abstract

“…Procedural and simulation-based methods often required meticulous parameter tuning to generate desired terrains and lacked intuitive ways to involve user control. In contrast, example-based methods used more intuitive user guidance such as sketches and images for terrain generation (spick and walker 2019; Li et al 2006). Zhou et al (2007) proposed a more direct user control scheme that blends patches from real terrains containing height fields with userdefined sketches.…”

Section: Example-based Terrain Generationmentioning

confidence: 99%

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

Hu,

et al. 2024

AAAI

View full text Add to dashboard Cite

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 is available at https://github.com/TDNResearch/TDN.

show abstract

“…The earliest data‐driven methods repurposed texture synthesis for terrain generation by cutting, reassembling, and joining terrain fragments at a patch or pixel level [LWZ*06,ZSTR07]. Subsequent research built on this foundation to improve: realism by altering patch blending [TGM12] and fixing global drainage [SD21,SD22], performance through GPU acceleration [TGM12, GMM15], and authoring control by extending beyond ridge and valley sketching [GMM15].…”

Section: Related Workmentioning

confidence: 99%

Interactive Authoring of Terrain using Diffusion Models

Lochner,

Gain,

Perche

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

Generating heightfield terrains is a necessary precursor to the depiction of computer‐generated natural scenes in a variety of applications. Authoring such terrains is made challenging by the need for interactive feedback, effective user control, and perceptually realistic output encompassing a range of landforms. We address these challenges by developing a terrain‐authoring framework underpinned by an adaptation of diffusion models for conditional image synthesis, trained on real‐world elevation data. This framework supports automated cleaning of the training set; authoring control through style selection and feature sketches; the ability to import and freely edit pre‐existing terrains, and resolution amplification up to the limits of the source data. Our framework improves on previous machine‐learning approaches by: expanding landform variety beyond mountainous terrain to encompass cliffs, canyons, and plains; providing a better balance between terseness and specificity in user control, and improving the fidelity of global terrain structure and perceptual realism. This is demonstrated through drainage simulations and a user study testing the perceived realism for different classes of terrain. The full source code, blender add‐on, and pre‐trained models are available.

show abstract

Example-Based Realistic Terrain Generation

Cited by 9 publications

References 10 publications

Region-Based Artificial Terrain Texture Generation

Region-Based Artificial Terrain Texture Generation

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

Interactive Authoring of Terrain using Diffusion Models

Contact Info

Product

Resources

About