Clouds play an important role in creating realistic images of outdoor scenes. Many methods have therefore been proposed for displaying realistic clouds. However, the realism of the resulting images depends on many parameters used to render them and it is often difficult to adjust those parameters manually. This paper proposes a method for addressing this problem by solving an inverse rendering problem: given a non-uniform synthetic cloud density distribution, the parameters for rendering the synthetic clouds are estimated using photographs of real clouds. The objective function is defined as the difference between the color histograms of the photograph and the synthetic image. Our method searches for the optimal parameters using genetic algorithms. During the search process, we take into account the multiple scattering of light inside the clouds. The search process is accelerated by precomputing a set of intermediate images. After ten to twenty minutes of precomputation, our method estimates the optimal parameters within a minute.

Synthetic images of outdoor scenes generated by computer graphics usually contain the sky as background. The appearance of the sky plays an important role in enhancing the reality of scenes. In this paper, we propose an intuitive and interactive system for synthesizing sky images that can reflect the user's intention. Our system consists of two steps. The first step is a sky generation step. The luminance distribution and colors of the sky are generated using our intuitive user interface. The second step is a cloud composition step. We have prepared a database of photographs of real clouds. Our system searches the database for cloud photographs that are suitable for the synthesized sky. The user selects the clouds in the search results and they are composited into the sky image. By using our system, the user can easily generate desired sky images.