Coherent multi-layer landscape synthesis

• Published in: The Visual computer Vol. 33; no. 6-8; pp. 1005 - 1015
• Main Authors: Argudo, Oscar, Andujar, Carlos, Chica, Antonio, Guérin, Eric, Digne, Julie, Peytavie, Adrien, Galin, Eric
• Format: Journal Article Publication
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01-06-2017; Springer Nature B.V; Springer; Springer Verlag
• Subjects: Algorithms; Approximation; Artificial Intelligence; Coherent multi-layer landscapes; Computer Graphics; Computer Science; Computer vision; Decomposition; Dictionary matching; Ecosystems; Elevation; Example-based modeling; Graphics; Humidity; Image Processing and Computer Vision; Informàtica; Intel·ligència artificial; Multilayers; Original Article; Rainforests; Realism; Simulation; Synthesis; Terrain; Vegetation; Visió per ordinador; Àrees temàtiques de la UPC; Dictionary matching; Example-based modeling; Coherent multi-layer landscapes
• ISSN: 0178-2789; 1432-2315; 1432-8726
• DOI: 10.1007/s00371-017-1393-6

We present an efficient method for generating coherent multi-layer landscapes. We use a dictionary built from exemplars to synthesize high-resolution fully featured terrains from input low-resolution elevation data. Our example-based method consists in analyzing real-world terrain examples and learning the procedural rules directly from these inputs. We take into account not only the elevation of the terrain, but also additional layers such as the slope, orientation, drainage area, the density and distribution of vegetation, and the soil type. By increasing the variety of terrain exemplars, our method allows the user to synthesize and control different types of landscapes and biomes, such as temperate or rain forests, arid deserts and mountains.