Understanding Bayesian rooms using composite 3D object models

as proposed in this paper enables better understanding of scenes, illustrated here by localizing chairs tucked under the table in 3D. We develop a comprehensive Bayesian generative model for understanding indoor scenes. While it is common in this domain to approximate objects with 3D bounding boxes, we propose using strong representations with finer granular-ity. For example, we model a chair as a set of four legs, a seat and a backrest. We find that modeling detailed geom-etry improves recognition and reconstruction, and enables more refined use of appearance for scene understanding. We demonstrate this with a new likelihood function that re-wards 3D object hypotheses whose 2D projection is more uniform in color distribution. Such a measure would be confused by background pixels if we used a bounding bo