In this paper we use neural network algorithms for office layout. A pixel matrix of coarse pixels is used to represent the objects of the room and their spatial relation. For each pixel the probabilities of the different objects are predicted from the neighboring pixels, assuming that the geometrical structure is mainly determined by local characteristics. Local receptive fields are employed to capture these local interactions using backpropagation networks. The reconstruction of the complete scene is achieved by an iterative process. Starting with given marginal constraints (or missing information for specific locations) each feature map performs an association with respect to its central pixel. This corresponds to the simulation of a Markov random field. External constraints on the sum of probabilities are taken into account using the iterative proportional fitting algorithm. The viability of the approach is demonstrated by an example.
Gerhard Paass, Gerhard Paass,
"Associative synthesis of geometrical scenes", Proc. SPIE 1766, Neural and Stochastic Methods in Image and Signal Processing, (16 December 1992); doi: 10.1117/12.130860; https://doi.org/10.1117/12.130860