S.: Scene parsing by integrating function, geometry and appearance models

Indoor functional objects exhibit large view and appear-ance variations, thus are difficult to be recognized by the traditional appearance-based classification paradigm. In this paper, we present an algorithm to parse indoor images based on two observations: i) The functionality is the most essential property to define an indoor object, e.g. “a chair to sit on”; ii) The geometry (3D shape) of an object is designed to serve its function. We formulate the nature of the object function into a stochastic grammar model. This model char-acterizes a joint distribution over the function-geometry-appearance (FGA) hierarchy. The hierarchical structur