Interactive Authoring of Terrain using Diffusion Models
dc.contributor.author | Lochner, Joshua | en_US |
dc.contributor.author | Gain, James | en_US |
dc.contributor.author | Perche, Simon | en_US |
dc.contributor.author | Peytavie, Adrien | en_US |
dc.contributor.author | Galin, Eric | en_US |
dc.contributor.author | Guérin, Eric | en_US |
dc.contributor.editor | Chaine, Raphaëlle | en_US |
dc.contributor.editor | Deng, Zhigang | en_US |
dc.contributor.editor | Kim, Min H. | en_US |
dc.date.accessioned | 2023-10-09T07:34:13Z | |
dc.date.available | 2023-10-09T07:34:13Z | |
dc.date.issued | 2023 | |
dc.description.abstract | 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 pretrained models are available. | en_US |
dc.description.number | 7 | |
dc.description.sectionheaders | Modeling by Learning | |
dc.description.seriesinformation | Computer Graphics Forum | |
dc.description.volume | 42 | |
dc.identifier.doi | 10.1111/cgf.14941 | |
dc.identifier.issn | 1467-8659 | |
dc.identifier.pages | 13 pages | |
dc.identifier.uri | https://doi.org/10.1111/cgf.14941 | |
dc.identifier.uri | https://diglib.eg.org:443/handle/10.1111/cgf14941 | |
dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
dc.title | Interactive Authoring of Terrain using Diffusion Models | en_US |
Files
Original bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- v42i7_13_14941.pdf
- Size:
- 5.32 MB
- Format:
- Adobe Portable Document Format