Cloud plays an important role in creating realistic outdoor scenes for video game and flight simulation applications.
Classic methods have been proposed for cumulus cloud modeling. However, these methods are not flexible for modeling
large cloud scenes with hundreds of clouds in that the user must repeatedly model each cloud and adjust its various
properties. This paper presents a meteorologically based method to reconstruct cumulus clouds from high resolution
Landsat8 satellite images. From these input satellite images, the clouds are first segmented from the background. Then,
the cloud top surface is estimated from the temperature of the infrared image. After that, under a mild assumption of flat
base for cumulus cloud, the base height of each cloud is computed by averaging the top height for pixels on the cloud
edge. Then, the extinction is generated from the visible image. Finally, we enrich the initial shapes of clouds using a
fractal method and represent the recovered clouds as a particle system. The experimental results demonstrate our method
can yield realistic cloud scenes resembling those in the satellite images.