Authoring Terrestrial Planets with Diffusion Models
Year: 2026
Type: article
Abstract: To support the design and subsequent generation of terrestrial planets for use in the creative media, we propose a solution that employs a generative model trained on satellite data from planetary bodies with a defined solid surface, such as the Earth and Mars. A user sketches coarse elevation, landcover, temperature, and precipitation directly onto a globe. Our model then infers high‐resolution heightmap and surface appearance layers at planetary scales, with sufficient detail to enable animated flyovers within the exosphere at a distance of a few thousand kilometers from the planet surface. We address the issue of distortion in the mapping from atlas to globe using a quadsphere representation, and the consistency of large‐scale geomorphological features by extracting a global river network from the sketch inputs and providing this as conditioning to the diffusion. As our results demonstrate, our generative model provides a balance between: authoring control through a multi‐layer painting interface with a satellite image pre‐visualization; computation times proportional to the surface area being generated; landscape diversity, displaying, without repetition artefacts, the full range of elevation and landcover features drawn from multiple source planets, and geomorphological plausibility through the provision of a consistent uninterrupted exorheic global river network, where the input sketches allow.
Source: Computer Graphics Forum
DOI: 10.1111/cgf.70390
Institutions: University of Cape Town, Centre National de la Recherche Scientifique, Laboratoire d'Informatique en Images et Systèmes d'Information, Institut National des Sciences Appliquées de Lyon, Lyon 1 Université, École Polytechnique, Laboratoire d'Informatique de l'École Polytechnique, Institut Polytechnique de Paris, Institut national de recherche en sciences et technologies du numérique, Université Côte d'Azur
Language: English
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $3,710
Funder: Agence Nationale de la Recherche
OpenAlex ID: W7160074131
