Scripting technology for generative modeling

In the context of computer graphics, a generative model is the description of a three-dimensional shape: Each class of objects is represented by one algorithm M. Furthermore, each described object is a set of high-level parameters x, which reproduces the object, if an interpreter evaluates M(x). This procedural knowledge differs from other kinds of knowledge, such as declarative knowledge, in a significant way. Generative models are designed by programming. In order to make generative modeling accessible to non-computer scientists, we created a generative modeling framework based on the easy-to-use scripting language JavaScript (JS). Furthermore, we did not implement yet another interpreter, but a JS-translator and compiler. As a consequence, our framework can translate generative models from JavaScript to various platforms. In this paper we present an overview of Euclides and quintessential examples of supported platforms: Java, Differential Java, and GML. Java is a target language, because all frontend and framework components are written in Java making it easier to be embedded in an integrated development environment. The Differential Java backend can compute derivatives of functions, which is a necessary task in many applications of scientific computing, e.g., validating reconstruction and fitting results of laser scanned surfaces. The postfix notation of GML is very similar to that of Adobes Postscript. It allows the creation of high-level shape operators from low-level shape operators. The GML serves as a platform for a number of applications because it is extensible and comes with an integrated visualization engine. This innovative meta-modeler concept allows a user to export generative models to other platforms without losing its main feature - the procedural paradigm. In contrast to other modelers, the source code does not need to be interpreted or unfolded, it is translated. Therefore, it can still be a very compact representation of a complex model