Interactive Authoring of Terrain using Diffusion Models

Lochner, D. and Gain, J. and Perche, S. and Peytavie, A. and Galin, E. and Guerin, E. (2023) Interactive Authoring of Terrain using Diffusion Models, Computer Graphics Forum, 42, John Wiley and Sons.

Text Diffusion Terrain.pdf Download (5MB)

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 pre- trained models are available.

Item Type:	Journal article (online only)
Uncontrolled Keywords:	machine learning, terrain authoring, terrain synthesis, nature simulation
Subjects:	Computing methodologies Computing methodologies > Computer graphics > Shape modeling
Date Deposited:	02 Nov 2023 15:42
Last Modified:	02 Nov 2023 15:42
URI:	https://pubs.cs.uct.ac.za/id/eprint/1583

Actions (login required)

View Item