Article Dans Une Revue Computer Graphics Forum Année : 2026

Authoring Terrestrial Planets with Diffusion Models

Oliver Borg
James Gain
Éric Guérin
Adrien Peytavie
Eric Galin

Résumé

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.

Fichier principal
Vignette du fichier
Computer Graphics Forum - 2026 - Borg - Authoring Terrestrial Planets with Diffusion Models.pdf (4.52 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-05608820 , version 1 (30-04-2026)

Licence

Identifiants

Citer

Oliver Borg, James Gain, Éric Guérin, Adrien Peytavie, Marie‐paule Cani, et al.. Authoring Terrestrial Planets with Diffusion Models. Computer Graphics Forum, 2026, 45 (2), pp.e70390. ⟨10.1111/cgf.70390⟩. ⟨hal-05608820⟩
12 Consultations
6 Téléchargements

Altmetric

Partager

  • More