Three-dimensional models are extensively used in nearly all types of computer graphics applications. The demand for 3D models is large and growing. However, despite extensive work in modeling for over four decades, model generation remains a labor-intensive and difficult process even with the best available tools.

We present a new procedural modeling technique called model synthesis that is designed to generate many classes of objects. Model synthesis is inspired by developments in texture synthesis. Model synthesis is designed to automatically generate a large model that resembles a small example model provided by the user. Every small part of the generated model is identical to a small part of the example model. By altering the example model, a wide variety of objects can be produced.

We present several different model synthesis algorithms and analyze their strengths and weaknesses. Discrete model synthesis generates models built out of small building blocks or model pieces. Continuous model synthesis generates models on set of parallel planes. We also show how to incorporate several additional user-defined constraints to control the large-scale structure of the model, to control how the objects are distributed, and to generate symmetric models. The generality of the approach will be demonstrated by showing many models produced using each approach including cities, landscapes, spaceships, and castles. The models contain hundreds of thousands of model pieces and are generated in only a few minutes.