Example-based synthesis of 3D object arrangements

Abstract

We present a method for synthesizing 3D object arrangements from examples. Given a few user-provided examples, our system can synthesize a diverse set of plausible new scenes by learning from a larger scene database. We rely on three novel contributions. First, we introduce aprobabilistic model for scenesbased on Bayesian networks and Gaussian mixtures that can be trained from a small number of input examples. Second, we develop a clustering algorithm that groups objects occurring in a database of scenes according to their local scene neighborhoods. Thesecontextual categoriesallow the synthesis process to treat a wider variety of objects as interchangeable. Third, we train our probabilistic model on a mix of user-provided examples and relevant scenes retrieved from the database. Thismixed modellearning process can be controlled to introduce additional variety into the synthesized scenes. We evaluate our algorithm through qualitative results and a perceptual study in which participants judged synthesized scenes to be highly plausible, as compared to hand-created scenes.