Our expertise in generative modeling is reflected by and related to several lectures, projects, as well experts.
We devise deep generative modeling algorithms for prediction of the localized disease progression.
Many steps in the modeling process are repeated several times with different parameters on different objects. Consequently, it is desirable to automate 3D modeling using some form of geometric programming language. When a user can specify variables and functions in a geometric program to let object parameters be computed automatically, even dynamic models become possible. Programmed models have a different space-time tradeoff: When low-level primitives are generated only on demand from higher-level descriptions, space is traded for model evaluation complexity. With a geometric modeling language that permits compact and comprehensive descriptions of very detailed models, this model description has to be quickly translated to graphics primitives at runtime. This leads to the following research directions:
efficient model evaluation and visualization
In fact, this approach initiates a paradigm change from traditional object-based modeling to function-based, i.e. generative, modeling. Objects are not described in terms of triangles anymore, but merely in terms of the function.
Generative Modeling explained
Generative Modeling is a field of research in machine learning, where the model is learned to emulate the actual process of data generation.